Agent City Wars

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of disclosure, yet it reveals nothing. It does not state that this is a mutation, what effects it has on game state, how idempotency_key is honored, or what permissions or prerequisites are needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is very short, but that brevity comes from under-specification rather than efficiency. The single sentence adds no information an agent could act on beyond the name itself.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating game action with two undocumented parameters, no annotations, and no output schema, the description supplies none of the context needed to invoke it safely or correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters. The description says nothing about city_id or idempotency_key semantics (format, whether the city must be owned by the caller, retry behavior), so it fails to compensate for the undocumented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name and maps it to an HTTP endpoint (POST /api/assign_line). It never says what an 'assign_line' actually does — assigning what, to what, in Agent City Wars. An agent cannot distinguish its purpose from siblings like train_assign or submit_actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to call this tool, when not to, or which sibling to prefer. The endpoint equivalence note gives no actionable selection criteria, leaving the agent to guess among 30+ sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it discloses nothing. It does not say whether this mutates state, consumes resources, requires ownership of the city, is reversible, or how idempotency is handled — all critical for an unannotated write-shaped action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short, but shortness here reflects under-specification rather than economy. The one substantive element — the REST endpoint reference — is not actionable for an MCP agent and occupies a slot that should hold purpose or behavioral detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an unannotated, mutating, two-parameter tool with no output schema and no documented return values, the description leaves every question unanswered. Nothing tells the agent what a successful build yields, what failures look like, or how the action integrates with the many sibling action tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters, and the description does not compensate at all: city_id and idempotency_key are never mentioned or explained. The meaning of idempotency_key (format, scope, reuse window) is entirely undocumented, and since required city_id is the only anchor, an agent cannot tell what identifies the build target.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ('build') with a game brand ('Agent City Wars action build') but never says what is being built — a building, a unit, a structure — or what the action costs or requires. The parenthetical pointing at 'POST /api/build' is a circular reference that adds no explanatory content and does not distinguish it from siblings like research, train_assign, or install_ram.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this tool, when not to, or which sibling to prefer for adjacent actions. An agent is left to infer from the name alone that this is a city-development action, with no prerequisites or eligibility conditions given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, yet it discloses nothing about consequences. It does not say whether ceding is irreversible, who gains the district, whether it costs resources or a turn, or whether idempotency_key protects against double-ceding — all critical for a likely state-mutating game action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is short but nearly all of it is wasted on the tool name plus a pointer to a REST endpoint that gives the agent no usable behavior. This is under-specification rather than earned conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation-style game action with zero annotation coverage, no output schema, and 0% parameter documentation, the description should explain effects, preconditions, and return behavior. It provides only the action's name and a REST analogue, leaving an agent unable to call it correctly with confidence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters, and the description adds no meaning: city_id's format/role and idempotency_key's semantics are both undocumented anywhere. The tool also allows additionalProperties, which the description does nothing to clarify.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ("Agent City Wars action cede_district") and points at an equivalent REST endpoint, but never explains what 'ceding a district' actually does in game terms. An agent learns it is a game action named cede_district and nothing more, which is essentially tautological against the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to cede a district versus alternatives such as trade_offer, trade_respond, or dispatch/recall actions, nor any stated preconditions (city ownership, district control, turn phase). The agent must infer usage entirely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, yet it says nothing about this being a mutating game action — no resource cost, no state effects, no idempotency behavior despite idempotency_key being a parameter, and no error/rate-limit context. The single sentence adds no behavioral information beyond the name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is brief, but brevity here is under-specification rather than conciseness — the one sentence is a name restatement plus an API mapping that gives an agent nothing actionable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating, unannotated game action with two undocumented parameters, no output schema, and 33 competing siblings, the description omits everything an agent would need: what the action consumes or produces, and when it is the right choice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description documents neither parameter. city_id (required) and idempotency_key have no format, valid-value, or semantic explanation anywhere, which is a serious gap for an action that presumably targets a specific city and supports safe retries.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name and equates it with an HTTP endpoint ("identical to POST /api/contribute_stockpile"). It never says what contributing a stockpile actually does in Agent City Wars terms, nor how it differs from the many other action siblings such as build, research, or trade_offer.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this action, what prerequisites exist, or which sibling action to prefer instead. The endpoint equivalence gives no help in choosing between contribute_stockpile and the 30+ other game actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing about cost, resource consumption, turn timing, failure modes, or reversibility. The only behavioral hint is implicit in 'POST /api/create_general', from which an agent can infer a mutating create operation, but that is minimal.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short line, so it is not verbose, but its brevity reflects under-specification rather than efficiency. The endpoint reference occupies space that could have carried the missing purpose or usage information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and 0% schema coverage, the description needed to supply the domain meaning, requirements, and parameter behavior. It supplies none of these, leaving the agent unable to call this tool correctly beyond guessing at city_id.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters, and the description says nothing about city_id or idempotency_key. The idempotency_key in particular has non-obvious retry semantics that the description entirely fails to explain.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ('create_general') and adds only that it is 'identical to POST /api/create_general', which is a tautological restatement of the same identifier. It never explains what a 'general' is in Agent City Wars or what the action accomplishes, so an agent cannot distinguish it from siblings like train_assign, research, or build.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this action versus the 30+ sibling actions, no prerequisites (e.g., needing a city, resources, or a turn), and no exclusions. The only context is a raw HTTP endpoint reference, which does not help tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full behavioral burden, yet it only implies mutation via 'action' and the POST endpoint reference. It does not state costs, cooldowns, whether the infiltrator can be lost, permission requirements, or how idempotency behaves.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is short and front-loaded, so there is no verbosity to trim. However, it is concise at the expense of substance, functioning more as a name echo plus endpoint mapping than a useful definition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation-style action with no annotations, no output schema, and undocumented parameters, the definition is far from complete. It gives no outcome, return, or failure-mode information an agent would need to invoke it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters (city_id required, idempotency_key optional), and the description says nothing about either. An agent gets no meaning for city_id or when/how to supply idempotency_key.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ('Agent City Wars action dispatch_infiltrator') and maps it to an HTTP endpoint, but never says what dispatching an infiltrator actually does in game terms. It does not distinguish this from siblings like dispatch_wave, recall_wave, or set_counterintel.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this action, what preconditions apply, or which sibling tool to choose instead. The only context is that it is an 'Agent City Wars action', which does not help an agent decide between it and the other dispatch or intrigue-related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden. The API-equivalence note weakly implies a mutation (POST), but it says nothing about cost, side effects, reversibility, idempotency semantics, or turn/authorization constraints for a game action that is likely consequential.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but brevity here reflects under-specification rather than efficiency; the one clause present (API equivalence) does little work for an agent. There is no front-loaded statement of action or effect.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a game-mutation tool with an idempotency parameter, zero annotation coverage, no output schema, and no parameter docs, the description is wholly inadequate. An agent could not confidently choose this over recall_wave or predict the outcome of calling it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters. The description does not explain what city_id identifies, whether it is the target or origin, or what an idempotency_key does here (its purpose is especially non-obvious in a turn-based game context). Two undocumented parameters with no compensating prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The text only restates the tool name and notes it is 'identical to POST /api/dispatch_wave'. It never says what dispatching a wave does in Agent City Wars — no mention of sending a force, attacking, moving units, or what a 'wave' is. The only added content is an API equivalence note, which is metadata rather than purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance at all, despite close siblings like recall_wave and dispatch_infiltrator that an agent must distinguish this from. There are no prerequisites, exclusions, or alternative-routing hints.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: no permissions or resources required to found an alliance, no cost, no irreversibility, no effect on existing alliance membership, and no response shape. The only hint of mutation is the verb 'found' and the POST endpoint reference.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but brevity here comes from under-specification rather than editorial discipline; the one sentence present conveys no information beyond the tool name and an API route.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a state-mutating game action with no annotations, no output schema, and zero parameter documentation, the description should explain eligibility, cost, and effects. None of that is present, so an agent cannot call this correctly without guessing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across two parameters. The description says nothing about city_id (required) or idempotency_key, which is exactly the parameter that needs explanation — whether retries with the same key are safe, and what value format is expected.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is essentially a restatement of the tool name plus an equivalent REST endpoint reference ('identical to POST /api/found_alliance'). It never states in plain terms that this creates a new alliance, nor does it distinguish the action from sibling tools like join_alliance or get_alliance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, prerequisites, or alternatives are given. The presence of join_alliance and get_alliance among siblings makes the missing differentiation especially costly, since an agent cannot tell founding from joining an existing alliance from this text.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It reveals only that this is a game action equivalent to a POST endpoint, implying a mutation, but says nothing about resource costs, prerequisites, irreversibility, or failure modes — essential for a state-changing game action.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but short because it is under-specified rather than efficient. The parenthetical endpoint mapping is low-value for an agent choosing a tool, while the information that actually matters is absent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, and 0% parameter documentation, the description leaves nearly every operational question unanswered — preconditions, cost, result, and sibling differentiation. It is not adequate for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for the single 'name' parameter, and the description adds no clarification. An agent must guess whether 'name' is the city name, a player name, or something else, and whether it is required (it is not listed as required).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The name and the phrase 'Agent City Wars action found_city' imply founding a city in a game, and the parenthetical maps it to POST /api/found_city. But the description never states the effect (creating a new city), what it costs, or how it differs from the sibling 'found_second_city', which is a critical distinction left to inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this versus alternatives. Given siblings like found_second_city and get_city, the description should say when founding is valid (e.g., first city only) and point elsewhere for subsequent cities, but it does none of that.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are supplied, so the description carries the full burden, and it discloses nothing: not whether the action mutates game state, consumes resources or a turn, is reversible, or requires prerequisites. The endpoint equivalence is not behavioral information an agent can act on.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but brevity here comes from omission rather than efficiency; the single clause is a tautology plus an unimplementable API reference, so no sentence earns its place by adding information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a state-mutating game action with unannotated optional idempotency and no output schema, the description omits cost, preconditions, effect on game state, and error behavior. It is far below what an agent needs to invoke it safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds nothing about either parameter. It does not say what city_id refers to (the existing home city that spawns the new one? the new city's id?) or why idempotency_key exists, leaving the required parameter ambiguous.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name and equates it to an HTTP endpoint ('identical to POST /api/found_second_city'), which conveys no meaning to an agent that cannot see the API. It never states what founding a second city does (cost, prerequisites, resulting state) and gives no differentiation from the sibling found_city.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of the obvious alternative found_city or any exclusion such as 'only after your first city reaches X'. The agent must guess entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing. 'get' implies a read, but there is no statement about authentication, whether membership is required, what happens if the city has no alliance, or whether idempotency_key matters for this read. The POST endpoint reference actually adds ambiguity about side effects rather than resolving it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded, but the brevity is under-specification rather than conciseness: the single sentence spends its words on the tool name and an endpoint alias instead of useful information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and no documented parameters, the description is the only source of behavioral context and it is nearly empty. It should at minimum explain what alliance data is returned and what preconditions apply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no parameter meaning whatsoever. It does not say what city_id identifies or why idempotency_key exists on a get operation, so an agent must guess both.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name and points at an HTTP endpoint, but never says what get_alliance actually returns or what scope it covers (the caller's alliance? a city's alliance?). It is essentially a tautology plus a routing note, leaving an agent unable to distinguish it cleanly from join_alliance, leave_alliance, or found_alliance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance at all: no prerequisites, no mention of when this is preferable to join_alliance/found_alliance, and no statement of what state the caller must be in. The endpoint reference is not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and discloses nothing: not whether the call is read-only, not what data is returned, not why a read operation accepts an idempotency_key, and not any auth/rate-limit behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the brevity comes from under-specification rather than discipline; the only substantive content is an API endpoint mapping of little use to an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No annotations, no output schema, 0% parameter documentation, and no return-value description leave an agent unable to call this correctly or interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the description adds no meaning for either parameter. The presence of an idempotency_key on a 'get' call is confusing and completely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name ('get_battle_report') and notes it mirrors a REST endpoint, which is a tautology rather than an explanation. It never says what a battle report is, what it contains, or how it differs from siblings like get_turn_packet or get_world_events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance whatsoever on when to call this versus the many other get_* read tools, and no prerequisites or exclusions. The endpoint-mapping parenthetical does not help an agent choose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it discloses only that the tool maps to a POST endpoint — a mildly useful hint that a nominally read-like action may have transport side effects or require an idempotency key. It says nothing about permissions, side effects, or what a call returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is front-loaded and free of waste, but that brevity stems from under-specification rather than disciplined editing. It is appropriately sized for what little it says.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A game-domain read tool with no annotations, no output schema, and zero parameter documentation needs far more description than this. An agent cannot determine return shape, identifier source, or idempotency requirements before calling it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description adds no meaning for either parameter. An agent gets no explanation of what city_id refers to or why/when an idempotency_key should be supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description mostly restates the tool name ("get_city") and adds only that it is equivalent to a POST /api/get_city call. It never states what a city object contains or what 'get' returns, so sibling tools like get_district and get_map remain indistinguishable by purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this tool versus get_map, get_district, get_turn_packet, or any other read tool. Neither prerequisites nor exclusions are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden and delivers almost nothing: no auth requirements, no error behavior, no note on whether the call mutates state. The presence of an idempotency_key parameter hints at possible side effects on a 'get' action, and the description does nothing to resolve that ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is short but not efficient: the parenthetical REST endpoint mapping is the only content and adds no value to an agent that cannot call HTTP endpoints. This is under-specification rather than conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and undocumented parameters, the description must do all the work and does none of it. An agent cannot determine what it receives back or what idempotency_key means, so the definition is not complete enough to invoke reliably.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters, so the description must compensate, and it adds no meaning for city_id or idempotency_key. The role of idempotency_key on a retrieval action is especially unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name ("get_district") and maps it to an HTTP endpoint ("identical to POST /api/get_district"). It never states what a district is, what data is returned, or how this differs from get_city or get_map, leaving purpose inferable only from the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this versus any of the ~30 siblings such as get_city, get_map, or get_turn_packet. The HTTP endpoint mapping conveys no usage context or preconditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and discloses nothing: not whether it is a read, not side effects, not required auth, not whether the idempotency_key matters for a 'get'. The fact that a read-like name maps to a POST endpoint is left entirely unexplained.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but brevity here comes from under-specification rather than economy. The single sentence is front-loaded with a tautology and then spends its back half on an endpoint mapping.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No annotations, no output schema, 0% schema description coverage, and an unexplained action-triggering POST behind a get_* name. Nothing an agent needs in order to call this correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the description says nothing about city_id (required) or idempotency_key. An agent has to guess the format of city_id and whether idempotency_key is needed or ignored on this call.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name and points at the backing endpoint (POST /api/get_house_challenges), which adds no semantic meaning. It never says what a 'house challenge' is, whether this reads challenges or triggers actions, or how it differs from sibling get_* tools like get_city or get_battle_report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to call this versus the many other get_* siblings, no prerequisites, no exclusion criteria. The only content is a name echo and an HTTP route reference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: no permission requirements, no cost/turn implications, no indication of whether the map is scoped to a city, no note on idempotency behavior despite an idempotency_key parameter.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is very short, but brevity here reflects under-specification rather than efficiency; the single parenthetical about the POST route is the only content and it does not help an agent act.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, and 0% parameter coverage, the description needed to explain inputs, scope, and return shape. It supplies none of these, so an agent cannot call this tool reliably.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters. The description never mentions city_id (required) or idempotency_key, leaving the agent with no meaning for either beyond their names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ('get_map') and adds only an HTTP route equivalence ('identical to POST /api/get_map'), which conveys no semantic meaning. It never says what a 'map' contains or how it differs from siblings like get_city, get_district, or get_world_events.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this rather than get_city, get_district, get_turn_packet, or any other read sibling. The only added information is a URL mapping, which does not help tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden and delivers nothing: it does not say whether the call is read-only (the 'get_' prefix implies read, yet it maps to a POST endpoint, which is confusing), whether it mutates state, whether it costs resources, or whether idempotency matters. For a state-reading tool in a game engine this is a critical omission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single short sentence, so there is no bloat, but it is under-specified rather than concise. The only informative fragment (the HTTP equivalence) is buried in a parenthetical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, 0% parameter coverage, and 32 sibling tools, this description supplies almost none of what an agent needs to call the tool correctly or predict its behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters, and the description adds no meaning: the format of city_id is unstated, and idempotency_key is unexplained even though its presence on a 'get' action is non-obvious and suggests side effects worth documenting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ("get_turn_packet") and adds only that it is identical to an HTTP endpoint. Nothing explains what a 'turn packet' is, what data it contains, or how it differs from siblings like get_city or get_map. The HTTP mapping is marginally informative but the purpose remains opaque.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to call this versus the dozens of sibling getters, no prerequisites, and no exclusions. The parenthetical about the POST endpoint is not a usage rule an agent can act on.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it discloses nothing: not whether this is a read, not scope of returned events, not pagination, not whether the idempotency_key matters for a get operation. The endpoint reference is not a behavioral trait an agent can act on.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but short by omission rather than by discipline. The single sentence is under-specified and spends its words on an API route reference rather than on the information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool in a complex multi-action game API, with zero parameter documentation, no annotations, and no output schema, the description is wholly inadequate. Nothing tells the agent what it will receive or how to interpret it, and no structured field compensates.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds nothing about either parameter. An agent must guess whether city_id scopes events to one city, whether it is required to be a city it controls, and what idempotency_key means for a 'get'-style action.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The text restates the tool name ('get_world_events') and adds an endpoint equivalence ('identical to POST /api/get_world_events') that conveys nothing about what the tool actually returns. It does not say what a 'world event' is, nor distinguish it from siblings like get_turn_packet, get_map, or get_battle_report, which are the obvious alternatives an agent would weigh.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to call this tool, when not to, or which sibling to prefer for world/state information. The agent is given no routing criteria at all.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure and delivers none. It does not say this is a mutating, resource-consuming action, whether it is reversible, what happens on repeat calls, or what a successful response contains — despite it clearly being a state-changing operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is a single short sentence with no filler, so it is concisely structured, but the brevity comes at the cost of substance rather than being tight and informative. The endpoint reference is the only content that earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating action tool with zero annotation coverage, no output schema, and fully undocumented parameters, this definition is completely inadequate. An agent would have to already know the game's rules to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters. The description says nothing about city_id (which city the RAM is installed in) or idempotency_key (whether retries are safe), so an agent has no documented meaning for either argument from schema or prose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ("install_ram") and maps it to a REST endpoint, but never says what installing RAM actually does in the game — whether it costs resources, increases a capacity stat, or attaches to a city. It is essentially a tautology plus an API route hint, giving an agent no more understanding than the name alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to install RAM, what prerequisites must hold, or how this differs from related siblings such as uninstall_ram. The natural pairing with uninstall_ram goes unmentioned, so the agent must guess at the selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and discloses nothing: not that this is a state-changing action, whether it requires an invitation or existing alliance, whether it is idempotent (the idempotency_key param hints at retry semantics but is unexplained), or what happens on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but terseness here is under-specification rather than conciseness; the single sentence adds no actionable information beyond the name and endpoint mapping.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A two-parameter mutation action with no annotations and no output schema needs at least a statement of effect, preconditions, and parameter meaning. None of that is present, so the definition is not sufficient to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description mentions neither parameter. city_id and idempotency_key are completely undocumented in both schema and description, including why an idempotency key is offered.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description essentially restates the tool name and adds an HTTP endpoint mapping ('identical to POST /api/join_alliance'). It does not explain what joining an alliance means in game terms or how it differs from found_alliance/leave_alliance/get_alliance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No indication of when to use this instead of siblings such as found_alliance, leave_alliance, or get_alliance, and no prerequisites (e.g., must the city not already be in an alliance, must the alliance exist). The only added information is an endpoint equivalence, which is not usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, yet it discloses nothing about effects, resource costs, turn timing, permissions, or side effects. The API endpoint note is not behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but brevity here reflects under-specification rather than efficiency. The single sentence spends its length on a name restatement and an endpoint pointer that add no usable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, 0% parameter coverage, and an unspecified mutation-like action, the description omits nearly everything an agent needs to invoke it correctly. It is not complete on any dimension.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description never mentions either parameter. city_id (required) and idempotency_key are left completely unexplained, so an agent cannot know what city_id refers to or how idempotency behavior works.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Restates the tool name ('Agent City Wars action launch_satellite') and adds only an API endpoint reference ('identical to POST /api/launch_satellite'), which conveys no meaning beyond the name itself. It never explains what launching a satellite does in game terms or how it differs from siblings like build or research.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool, prerequisites, costs, or alternatives among the many sibling actions. An agent has no basis to choose launch_satellite over build, research, or dispatch_wave.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it discloses nothing: whether membership is forfeited irreversibly, whether leadership must be transferred first, what happens to contributed stockpiles, or any error conditions. The endpoint reference adds no behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is short but that brevity is under-specification rather than conciseness. The only content is a name restatement plus an API path that gives the agent no actionable information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a state-changing membership tool with no annotations, no output schema, and zero-documented parameters, the description omits everything an agent would need: effects, irreversibility, required permissions, and return behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters, and the description mentions neither city_id nor idempotency_key. An agent gets no hint that idempotency_key exists for safe retries or why city_id is required for an alliance-leaving action.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description essentially restates the tool name ('Agent City Wars action leave_alliance') and maps it to an HTTP endpoint. It never explains what leaving an alliance actually entails, and it does nothing to distinguish this tool from siblings like join_alliance or found_alliance beyond the verb embedded in the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to invoke this versus alternatives such as join_alliance or found_alliance, and no mention of prerequisites (e.g. whether the caller must be a member, whether leaders can leave). Usage must be fully inferred from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the entire burden and discloses nothing: not whether this is a read or a mutation, not authorization requirements, not side effects, not idempotency behavior. The presence of an idempotency_key parameter hints at write semantics that the description never confirms or denies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The text is short, but brevity here comes from under-specification, and the parenthetical endpoint reference adds no actionable meaning for an agent. Nothing is front-loaded because there is no substance to order.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter action tool with no annotations, no output schema, and no schema descriptions, the description should explain purpose, side effects, and parameter meaning. It does none of these, leaving the agent unable to invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description supplies nothing about either parameter. It does not explain that city_id is the required scope key or what idempotency_key should contain or when it must be supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name ("operator_query") and points to an HTTP endpoint of the same name, which is a tautology rather than an explanation. It never says what is being queried (operator status? pending actions? turn state?) or how it differs from sibling read tools like get_city, get_map, or get_turn_packet.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to call this versus the many sibling query tools, no prerequisites, and no exclusions. An agent has no basis for choosing operator_query over get_turn_packet or get_city.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it discloses nothing: no side effects, no cost/resource implications, no reversibility, no indication of whether idempotency_key matters or what happens on repeat calls. For a game action that evidently mutates state, this is a critical gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is brief, but the brevity is under-specification rather than economy; the parenthetical about the REST endpoint is noise for an MCP agent, and there is no useful front-loaded information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no annotations, no output schema, 0% schema coverage, and 33 sibling tools, the description supplies none of the context needed to invoke this action safely or correctly. It is essentially a name plus an endpoint alias.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for two parameters (city_id, idempotency_key), and the description adds no meaning at all — not even which city the wave belongs to or how the idempotency key should be formed. It fails to compensate for the undocumented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name and notes it is identical to an HTTP endpoint, which is tautological rather than explanatory. It never says what a 'wave' is, what recalling one does, or how it differs from sibling tools like dispatch_wave.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Labeling it an 'Agent City Wars action' implies a game context but gives no condition for when to use it, no prerequisites, and no contrast with the many siblings (dispatch_wave, submit_actions, etc.). An agent has to infer everything.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, and it discloses nothing: not whether the action is a state mutation, what resources or turns it consumes, what it returns, or whether idempotency is required to prevent double submission. The single parenthetical adds no behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short and front-loaded, with no padding or rambling. But the single parenthetical pointing at a REST endpoint earns little of its place for an MCP agent, so brevity here reflects under-specification rather than discipline.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a state-mutating game action with no annotations, no output schema, and two undocumented parameters, the description supplies none of the context an agent needs before invoking it. Nothing about effects, costs, or return values is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters, and the description says nothing about city_id (which city's research? must it be owned?) or idempotency_key (what retry semantics does it enable?). With zero compensation for an undocumented schema, this is a clear failure.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name ('action research') and points at a REST endpoint, so it is essentially tautological. It never says what 'research' accomplishes in the game (e.g. generating research points, advancing a tech tree), which is needed to distinguish it from siblings like build, train_assign, or install_ram.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No indication of when to use this action versus the ~30 sibling actions, no prerequisites (turn phase, city ownership, cost), and no exclusions. The only signal is that it maps to POST /api/research, which an agent cannot act on without the API docs.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing: not the effect of setting a banner, whether it is reversible, its cost or turn implications, or why an idempotency_key exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the brevity comes from under-specification rather than efficiency—the single sentence repeats the name and an endpoint path, both of which the agent already has.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, and 0% parameter coverage, the description supplies none of the context needed to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no meaning for either city_id or idempotency_key. The agent is left to guess formats, constraints, and idempotency semantics entirely.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description merely restates the tool name ('Agent City Wars action set_city_banner') and points to an HTTP endpoint. It never explains what a city banner is, what setting it does, or how it differs from siblings like set_counterintel or set_standing_order.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to call this versus the many other Agent City Wars action tools. The reference to POST /api/set_city_banner gives no condition, prerequisite, or alternative that would help an agent choose.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, and it discloses nothing: no cost, resource consumption, turn timing, reversibility, or prerequisites. The POST endpoint reference faintly implies a state mutation but gives no usable behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the brevity comes from under-specification rather than economy. The parenthetical REST endpoint reference consumes half the text and provides no decision value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a game-mutation action with no annotations, no output schema, and zero parameter documentation, the description supplies none of the context needed to invoke it correctly. An agent would have to guess at the action's effect and its preconditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so both city_id and idempotency_key are entirely undocumented, and the description adds no meaning for either. The idempotency_key name hints at retry safety but the description leaves the agent to infer that, and the additionalProperties:true surface is unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name plus an opaque REST endpoint mapping ("identical to POST /api/set_counterintel"). It never says what setting counterintelligence does in Agent City Wars, and it offers no distinction from siblings like dispatch_infiltrator or install_ram that plausibly relate to the same espionage domain.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use, when-not-to-use, or alternative-tool guidance. An agent cannot tell whether this should be called before, after, or instead of dispatch_infiltrator, assign_line, or submit_actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only notes equivalence to POST /api/set_standing_order, without saying whether the action is idempotent, what permissions are required, what gets changed, or what happens if a standing order already exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single sentence is short but not informative; it is under-specified rather than concise. There is no front-loaded explanation of purpose, behavior, or usage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation-style game action with no annotations, no output schema, and undocumented parameters, the description is completely inadequate. It leaves the agent unable to call the tool correctly or understand its effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no meaning for city_id or idempotency_key beyond their names. With two parameters and no schema documentation, the description should compensate but does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description largely restates the tool name and gives an API endpoint reference, but it never explains what a 'standing order' is or what setting one actually accomplishes. An agent can tell this is some action in Agent City Wars, but not the specific operation it performs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool, when not to use it, or which sibling action it replaces or complements. The agent is left with no routing information among the many other game actions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, yet it discloses nothing: not whether submissions are batched, whether they consume a turn, whether they are validated atomically, or what happens on partial failure. The only hint, that it maps to an HTTP POST, tells the agent almost nothing about behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the brevity comes from under-specification rather than efficiency. The parenthetical endpoint reference consumes the only content slot that could have explained the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A mutation tool with three undocumented parameters, no annotations, no output schema, and no explanation of the payload contract. Nothing an agent needs in order to call it correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters (city_id, actions, idempotency_key) have 0% schema description coverage and the description says nothing about any of them. The 'actions' array in particular is untyped and undocumented, so an agent has no way to know what element shape to send.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name plus a project label and notes it is identical to POST /api/submit_actions. It never says what an 'action' is or what submitting one accomplishes, so an agent cannot distinguish this from assign_line, dispatch_wave, research, or other sibling actions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use, when-not-to-use, or alternative guidance at all. With 33 sibling tools in a game where many are action-submitting commands, the absence of routing guidance is a serious gap.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden and discloses nothing: not that this is a mutating action, not what permissions or resources are required, not what an idempotency_key protects against, and not whether an offer can be withdrawn or expires.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but the single clause that exists is an endpoint cross-reference that conveys no usable information to an agent. Brevity here comes from under-specification, not from disciplined writing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutation tool with no annotations, no output schema, and 0% parameter coverage, the description supplies none of the missing context. An agent cannot call this correctly without guessing at the payload contents and consequences.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and both parameters (city_id, idempotency_key) are bare strings with no description, enum, or format. The description adds nothing — it never explains whose city_id is meant or when an idempotency_key should be supplied.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name plus a 'POST /api/trade_offer' endpoint mapping, which is a tautology rather than an explanation. It never says what a trade offer actually is (an offer of goods/stockpile to another city), who it targets, or how it differs from the sibling trade_respond.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of the obvious alternative, trade_respond. An agent has no basis for choosing between the two trade tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full disclosure burden, and it discloses nothing: not whether this mutates state, what happens on success, whether a matching open offer is required, or how idempotency_key behaves. The HTTP-route equivalence adds no behavioral information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but that brevity is under-specification rather than concision — the single sentence is a name restatement plus a route pointer, with no useful content to front-load.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A no-annotation, no-output-schema mutation tool with an unexplained two-parameter schema needs a real explanation of purpose, effect, and required identifiers. Nothing an agent needs in order to call it correctly is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description explains neither parameter. Notably, only city_id is required and there is no trade/offer identifier, which is exactly the kind of schema ambiguity the description should resolve but does not.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description restates the tool name plus an HTTP route equivalence ('identical to POST /api/trade_respond') without ever saying what the action does — presumably responding to a trade offer, but accept vs. decline vs. counter is never stated. Against a sibling set that includes trade_offer, this leaves the verb's effect ambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no mention of trade_offer or any alternative, and no preconditions. An agent picking among 33 siblings gets zero signal about when this action applies.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full disclosure burden, yet it says nothing about mutation effects, cost, authorization, or reversibility. Even the presence of an idempotency_key parameter goes unmentioned in behavioral terms.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The single parenthetical sentence is short and front-loaded with the tool name, so there is no bloat. However, brevity here reflects missing content rather than efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an unannotated, undocumented, mutation-shaped action with two opaque parameters and no output schema, the description provides nothing an agent needs to invoke it correctly or safely.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters. The description does not explain what city_id refers to or why an idempotency_key exists, so nothing compensates for the undocumented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name and notes it maps to POST /api/train_assign. It never says what 'train_assign' actually does (assigning a general to training? training assignment in a city?) nor how it differs from sibling tools like assign_line or create_general.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no indication of when to use this action, prerequisites (does the city need a barracks?), or which sibling tool to use instead. The agent is left to infer everything from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, yet it discloses nothing: not whether RAM removal is reversible, whether resources are refunded, whether idempotency_key prevents duplicate uninstalls, or what permissions/ownership are required. The only added detail is an HTTP endpoint mapping, which is not behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

It is short, but short here means under-specified rather than efficient. The single parenthetical about the POST endpoint consumes the only available space without telling the agent anything actionable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an unannotated mutation tool with two undocumented parameters and no output schema, the description should explain effect, side effects, and return behavior. It explains none of these, leaving the agent unable to call it correctly with confidence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for both parameters, and the description adds nothing about city_id or idempotency_key. In particular, the meaning and deduplication semantics of idempotency_key are left entirely unexplained, which is a real risk for a mutation action.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description only restates the tool name ('uninstall_ram') and maps it to an HTTP endpoint, which is a tautology rather than an explanation of what uninstalling RAM does in the game. It gives no sense of the effect, cost, or resource involved, and never distinguishes it from the sibling install_ram.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no prerequisites, and no mention of the obvious alternative install_ram. An agent must infer entirely from the name when this action is appropriate versus other city actions like build or research.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.