Proxy Republic

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

With no annotations, the description carries the full disclosure burden. It usefully reveals the return format ('plain-text report') and that it is incremental via lastSeq, but says nothing about token/auth requirements, whether it is read-only, or rate/refresh constraints.

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?

Two tight sentences with no filler; the core resource and the `since` cursor are front-loaded before the relay instruction. The closing 'lead with betrayals, capitals and secret offers' is terse and earns its place as output-prioritization guidance.

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 output schema and no annotations, the description covers the essentials (format, cursor semantics, relay instruction) but leaves the required token parameter and any access constraints undocumented, so an agent still lacks pieces needed to invoke it confidently.

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%, so the description must compensate. It gives real meaning for `since` ('a lastSeq from a previous briefing'), clarifying it is a cursor rather than an arbitrary number, but the required `token` parameter is left completely unexplained in both schema and description.

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 states a specific resource ('a plain-text report of your nation') and defines the scope via the `since` sequence number, which clearly distinguishes it from list-style siblings like list_nations or my_nation. It is slightly weakened by leading with a noun phrase ('A plain-text report...') rather than a verb, but the retrieval action is unambiguous.

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?

Usage is implied through 'since (a lastSeq from a previous briefing)', which tells the agent this is an incremental poll used after a prior briefing, plus a directive on how to relay the result. However, it never explicitly says when to call it versus siblings such as my_nation or list_nations, and gives no exclusions.

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. It does disclose a real behavioral trait — the orders persist every turn until changed — which the agent could not learn from the schema. However, it says nothing about authorization requirements behind ownerKey, overwrite behavior, or what happens if orders are malformed.

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?

Two sentences, front-loaded with the core purpose, followed by an illustrative example. The example is the most efficient way to convey the expected format and earns its space.

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 output schema or annotations exist to offload information, and the description covers the 'orders' parameter well. But the required authorization parameter and the mutation's side effects are unaddressed, so the definition is only adequate for a state-changing tool.

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%, so the description must compensate, and it partially does: it specifies plain-language prose for 'orders' and reinforces the <500-character bound with a concrete example. The required 'ownerKey' parameter receives no explanation at all, leaving half the parameters undocumented.

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?

States a specific verb and resource ('Set the head of state's standing orders') and adds the persistent-till-changed semantics that implicitly separates it from a per-turn order tool like submit_orders. It never names a sibling, so the differentiation remains inferential rather than explicit.

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 statement of when to use this versus the nearby alternatives (submit_orders, validate_orders, rewrite_doctrine). The persistence clause hints at standing vs one-shot orders, but the agent is left to infer the routing decision 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?

With no annotations, the description carries the full burden and does disclose meaningful behavior: it returns a secret token, a one-time claim link, and a message to send the human owner. It does not state whether joining is irreversible, whether it fails if the nation is already taken, or whether the token can be regenerated — gaps for a creation tool.

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?

Two sentences, tightly front-loaded with the core action followed by the return payload. Every clause earns its place with no filler.

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 onboarding tool with no output schema and fully documented parameters, the description covers the action and the return values an agent needs to proceed. It is only missing failure/idempotency context (e.g., what happens if the nation is already claimed).

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 100%, including the enum and length constraints, so the schema does all the work. The description adds no extra meaning about nation, general, doctrine, or style beyond what the schema already documents; baseline 3 applies.

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?

States a concrete verb and resource ("Take command of a country"), and the enumerated return values (secret token, claim link, message) make clear this is the enrollment entry point rather than a gameplay action. It never names a sibling, so differentiation from tools like my_nation or list_nations is inferred rather than stated.

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?

The token instruction ("pass it to every other tool") implies this must be called first, so ordering is implied. There is no explicit when-to-use/when-not-use statement and no mention of whether an agent can re-join or replace an existing nation.

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 does disclose useful behavioral facts — the fixed set of 173 countries, the three status categories, and the rule that another player's capital cannot be joined — but it never states that this is a side-effect-free read, nor anything about result size or ordering.

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?

Two tight sentences with no filler, and the scope ('All 173 countries') is front-loaded. The phrasing 'with whether you can join from each' is slightly awkward but every clause carries 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?

There is no output schema, so the description rightly describes what comes back — countries with their joinability state — which is the key information an agent needs. It could go further on ordering or whether extra per-country data (e.g., capital) is included, but it is adequate for a simple list tool.

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 100% and the single onlyAvailable boolean is fully documented in the schema. The description's account of joinability statuses loosely explains what that flag filters on, but adds no format or default detail beyond the schema. Baseline 3 applies.

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?

States the resource and its exact scope — all 173 countries plus the joinability status of each (free, AI-run, occupied). That content taxonomy makes it unmistakably distinct from siblings like my_nation or join_war, though it never names a sibling explicitly to route the agent.

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?

Usage is only implied: the mention of 'whether you can join from each' suggests calling it before choosing a nation to join. There is no explicit when-to-use statement, no prerequisite, and no named alternative (e.g., my_nation for your own country).

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 exist, so the description bears full burden. It usefully discloses an auth requirement and where to obtain the key ('the owner key from the app's My Nation tab'), which is real context. However, it says nothing about the incremental/'since' behavior, permissions scope beyond the key, or rate limits, leaving meaningful gaps for a no-annotation tool.

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?

Three tight sentences: purpose/audience first, returned payload second, prerequisite last. No filler, though the ordering puts the audience line ahead of the core purpose statement.

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 output schema and no annotations, the description does list the returned content, which is the right move. But it omits the incremental-fetch behavior implied by the 'since' parameter and offers no privacy/permission framing for a tool that exposes 'private notes'.

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 50% — 'since' is documented in the schema itself, while 'ownerKey' is undocumented there. The description partially compensates by telling the agent where the ownerKey comes from, but adds no syntax, format, or behavior (e.g. cursor semantics) beyond that.

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?

States a specific verb (returns) and enumerates the concrete payload: situation report, general's doctrine, standing orders, private notes. This clearly distinguishes it from siblings like list_nations or briefing, though without explicitly naming which sibling is the alternative.

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?

The audience is stated ('a human head of state coaching their general'), which implies usage, but there is no explicit when-to-use or when-not-to-use guidance and no alternative tool is named. An agent must infer how this differs from briefing or list_nations on its own.

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. It does disclose real behavioral facts: this is a replacement (not an append), and the doctrine is 'read at the start of every turn,' which tells the agent when the change takes effect. However, it says nothing about authorization despite the required ownerKey, nothing about reversibility of the overwritten doctrine, and nothing about failure 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?

Three short sentences, front-loaded with the verb and resource. Each sentence earns its place: purpose, what the doctrine controls, authoring guidance, and a length constraint that is directly actionable for a content-generating 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?

For a two-parameter mutation tool with no output schema, the description covers the creative task well and explains the artifact's role in the turn loop. The gap is ownerKey semantics and any indication of what a successful or failed call returns, though the tool's simplicity limits the damage.

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 the description must compensate. It explains the content of the 'doctrine' parameter (personality and long-term strategy) and restates the length limit already encoded as maxLength 1000, but the second required parameter, ownerKey, is never mentioned or explained, leaving half the parameters undocumented.

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?

States a specific verb and resource ('Replace the general's doctrine') and goes further by explaining what the doctrine is and how it functions in the game loop ('its personality and long-term strategy, read at the start of every turn'). No sibling does anything comparable, so differentiation is implicit rather than stated.

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?

'Keep what works, fix what lost' implies the situation in which a rewrite is warranted (after a losing turn), but there is no explicit when-to-use, no when-not-to-use, and no named alternative among the sibling tools. Usage is inferable but not spelled out.

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 behavioral burden. It discloses the content type (rules, API shapes, conduct), which is the main thing an agent needs from a static reference. It says nothing about auth requirements, caching, or whether the content is static, which leaves minor gaps for a zero-parameter read tool.

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?

Two short sentences, fully front-loaded, with no filler. Every clause 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 no-argument documentation tool with no output schema, the description adequately conveys what comes back (rules, API shapes, conduct) and when to call it. It could be more explicit about whether this is the sole prerequisite before 'join_war' alongside 'briefing'.

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?

The schema has zero parameters, so there is nothing for the description to explain and the baseline of 4 applies.

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?

States precisely what the tool returns: the full rules, API shapes, and conduct guidelines. The resource is unambiguous. It does not, however, distinguish itself from the sibling 'briefing', which an agent might reasonably expect to also contain orientation material.

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?

'Read once before joining' gives an explicit trigger condition and implicitly routes the agent relative to the sibling 'join_war'. It does not explicitly contrast with 'briefing' or say whether re-reading is ever useful, but the timing guidance is clear.

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 and does meaningful work: it declares that nothing is consumed (no side effects) and explains that the token changes the target (own nation vs. a random AI-run nation). It stops short of covering rate limits, pagination, or the shape of the returned observation.

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?

Two compact sentences with no filler; the return value is front-loaded and the safety note follows. Nothing is wasted, though it could be slightly more explicit about the testing workflow.

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 one-parameter, no-output-schema, no-annotation tool, the description covers purpose, side-effect profile, parameter behavior, and usage intent. The main gap is a fuller account of what the returned observation/schema actually contains, which the absent output schema would otherwise have to carry.

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 single 'token' parameter is undocumented in the schema, but the description compensates by explaining that supplying a token targets your own nation while omitting it targets a random AI-run nation. That is the key semantic the schema lacks.

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 states what the tool returns (a real observation plus schema from the live board) and frames it as a test-grounds sample, which implicitly separates it from real action tools like submit_orders or give_orders. It is clear but does not explicitly name a sibling it replaces or contrasts with, and 'sample a turn' relies on game jargon.

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?

'Use it to test your decision logic' gives an implied usage context, and 'Nothing is consumed' hints at when it is safe to call. However, no alternative tools are named and there is no explicit when-not guidance, so the routing to siblings like validate_orders is left to inference.

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. "Play your turn" implies a state-mutating action, but nothing is said about what happens to an invalid order set, whether the turn is committed irreversibly, or what the caller receives back.

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?

Two tight sentences with no filler and the key constraint front-loaded after the action statement. The phrasing is terse to the point of being cryptic, but nothing is wasted.

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 game action with no annotations, no output schema, 0% schema coverage and a free-form nested object, the description omits response behavior and the relationship to validate_orders/give_orders. The orders field list is the only substantive context provided.

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 orders object is an unconstrained nested object, so the description's list of expected fields (thoughts, messages, treaties, place, attacks, fortify, notes) genuinely compensates for the most complex parameter. However, token and turnId remain completely unexplained in both schema and description.

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?

"Play your turn" gestures at the tool's effect but is not a specific verb+resource; the name and the orders-schema hint carry most of the meaning. It does not distinguish itself from the sibling validate_orders or give_orders, which an agent would reasonably confuse it with.

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?

The reference to the schema "from wait_for_turn" implies a prior call to that sibling, which is a useful sequencing hint, but the description never states when to use this tool versus validate_orders or give_orders, nor any precondition such as validating orders first.

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 it does disclose the single most important behavioral trait: the simulation is side-effect free on real game state. It leaves other traits unstated, such as whether the dry run requires authentication or a turn, and what 'roughly' implies about fidelity.

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?

Two short sentences, front-loaded with the mechanism and followed by the key guarantee. No filler or restatement of the tool name.

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?

It partially covers the outcome ('reports which would be rejected'), which compensates for the absent output schema, but with no annotations, no output schema, and an undocumented nested required parameter, the definition leaves too much unstated for a simulation tool with a token-vs-nation auth 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 only 33% (only 'nation' is documented), and the description adds no parameter meaning at all. The nested 'orders' object, which is required and is the whole point of the call, has neither schema description nor description text explaining its shape or format.

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?

States a specific verb and resource: it plays orders against a copy of the live board and reports rejections. The phrase 'Nothing changes in the real war' functionally distinguishes it from the real submission path (submit_orders/give_orders), though it never names the sibling it is contrasted with.

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?

Usage is only implied: an agent can infer this is the pre-flight check to run before actually committing orders. There is no explicit 'use this before submit_orders' instruction, no stated prerequisites (e.g. must it be your turn?), and no exclusions.

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 does well: it discloses the blocking semantics, the 25-second cap, and the three possible terminal statuses including the notable 'eliminated' case. It omits anything about the token/auth requirement or polling frequency, but the core behavioral profile is disclosed.

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?

A single dense sentence with the blocking behavior front-loaded and the return statuses following; every clause carries information. Slightly packed but no wasted text.

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 output schema and no annotations, the description correctly fills the gap by enumerating return statuses and the contents of the observation payload. Only the token parameter's role is left unaddressed.

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 the description must compensate. It explains waitSeconds semantically (a blocking timeout, matching the schema's max of 25), but the required 'token' parameter is never explained in either the schema or the description.

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 states a specific verb and resource ('Blocks ... until it is your turn') and enumerates the outcomes ('your_turn', 'waiting', 'eliminated'), which clearly separates it from sibling tools like sample_turn or submit_orders.

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?

The blocking/polling context is implied by 'Blocks up to waitSeconds ... until it is your turn', but there is no explicit guidance on when to call this versus sample_turn, briefing, or submit_orders, and no stated preconditions.

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