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

With no annotations, the description carries the full behavioral burden. It discloses that an exact confirmation phrase is required, but it does not explain the effects of arming, safety implications, preconditions, or what state changes occur.

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 two short sentences with no wasted words. The core action is front-loaded, and the critical confirmation constraint is stated concisely.

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 safety-related state-changing tool, the description omits important context such as token provenance, preconditions, and consequences of arming. The output schema may cover return values, but the missing operational context makes the tool difficult 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%, so the description must compensate. It clearly defines the required literal value for confirm, but the token parameter remains completely unexplained, leaving a significant gap.

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: 'Arm the chassis interlock.' This is clear and distinct from siblings such as disarm_interlock and interlock_status, though it does not explicitly differentiate itself by 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 about when to use this tool versus alternatives like disarm_interlock or interlock_status. The confirmation phrase is a parameter constraint rather than usage context, so the agent is left to infer the appropriate scenario.

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 behavioral disclosure burden. 'Status' and the tool name 'identify' imply a non-mutating read, but the description never explicitly states that it makes no changes, requires no special context, or has no side effects.

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 extremely concise and scannable, using only one short phrase with no filler. It would benefit from being a complete sentence with a verb, but it is not bloated or repetitive.

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 zero-parameter tool with an output schema, the description is mostly workable: it says what domain the output covers. However, it lacks an explicit read-only statement and does not help the agent choose this tool over topology- or status-related siblings, leaving some contextual ambiguity.

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 input schema has zero parameters, so there are no parameter semantics for the description to add. The baseline of 4 applies; the description does not mislead about any arguments.

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 names concrete content areas ('Backend, driver, topology and current chassis status') so an agent can tell it is about chassis identification/status, not just a tautology. However, it lacks a verb such as 'get' or 'retrieve,' and it does not explicitly distinguish the tool from siblings like verify_topology.

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 tool is for reading chassis status/identity from the listed fields. There is no explicit 'use when' guidance, no mention of alternatives, and no exclusions, so the agent is left to reason about when it is preferred over 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?

No annotations are present, so the description carries the burden of disclosing side effects. It clearly states that the operation affects every card and destroys all routes, making the destructive and broad nature transparent. It could add an explicit irreversibility warning, but the core behavior 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?

The description is one concise sentence, front-loaded with the primary action and scope. Every word contributes meaning, with no filler or repetition.

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 global destructive tool, the description names the complete scope and both effects in a single sentence. An output schema exists, so return-value details need not be covered. It stops short of adding explicit caution or operational context, but nothing critical is missing 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?

The schema defines only a required 'token' string with no description, and the description does not discuss parameters. However, with a single self-explanatory authentication token, the lack of parameter explanation is not a practical obstacle for the agent.

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 uses a specific verb ('Open'), states the full scope ('every crosspoint on every card'), and adds a second clear effect ('forget all routes'). This distinguishes it from siblings like set_crosspoint or unroute_signal, which target individual elements.

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 wording 'every card' and 'all routes' implies a global reset, but the description never explicitly states when to use this tool versus individual operations like unroute_signal or set_crosspoint. Some guidance is inferable from the global scope, so it is not completely absent.

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 reveals two outputs but does not state that this is a read-only/non-mutating operation, nor does it describe error behavior, empty-route behavior, or what happens with invalid coordinates. For a state query, this leaves important behavioral context unstated.

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 and has no filler, and the key reported information is front-loaded. However, the description is so terse that it reads as under-specification rather than deliberate conciseness, leaving important invocation details out.

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 four required, fully undocumented parameters and zero annotations, this one-sentence description is not enough for reliable invocation. The output schema may clarify return shape, but the agent still lacks parameter semantics, usage guidance, and behavioral expectations. The description only tells what the tool reports, not how or when to call 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 no meaning to the four required parameters: card, subunit, row, and column. It does not explain how these identify a crosspoint, what formats or ranges are valid, or what card/subunit refer to. The word 'crosspoint' only repeats the tool name and does not compensate for the undocumented parameters.

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 identifies a specific query intent ('whether one crosspoint is closed') and names the resource and a second output ('which routes are holding it'). It is distinguishable from mutating siblings like set_crosspoint and route_signal, although it does not explicitly use a verb like 'gets' or 'returns'.

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. The description does not mention set_crosspoint, route_signal, or list_routes as related tools, nor does it state any preconditions such as requiring a known card or reserved crosspoint. The status-query phrasing implies a use case, but the agent is not told how to choose among siblings.

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 disclosure. It clearly states the two core behavioral effects: existing open routes are not disturbed, and no new routes can be created. It does not cover reversibility or authorization details, but the main side effects are transparent.

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 consists of two short, front-loaded sentences with no filler. The main action is stated first, and the clarifying behavioral note is concise. Every sentence 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?

The description explains the routing effects but omits the meaning of the required token parameter and does not mention how the operation can be reversed. While the output schema may cover return values, the missing parameter semantics and lack of annotations leave an agent with a meaningful gap 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?

The schema has one required parameter, 'token', with 0% description coverage, and the tool description never mentions it. The agent is left to guess whether the token is an auth credential, a resource identifier, or something else. With such low schema coverage, the description needed to compensate and did 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?

States a specific verb and resource: 'Disarm the interlock.' The second sentence clarifies the operational effect—existing routes remain, new routes are blocked—which makes the tool's role clear and distinguishes it from siblings like arm_interlock and interlock_status without needing their schemas.

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 description implies when to use the tool: when you want to stop new routes from being created while keeping current routes up. However, it does not explicitly state when not to use it or point to alternatives like arm_interlock or clear_all_routes, so the guidance remains implied rather than explicit.

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 must carry the behavioral transparency burden itself. The phrase 'whether the interlock is armed' strongly implies a read-only status inspection with no side effects, but it never explicitly states that. It also does not disclose permission requirements, error behavior, or whether the tool reflects a cached or live state.

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 compact phrase with no filler or redundancy. It front-loads the core subject and is easy to scan. A complete sentence with a verb would be slightly more polished, but the current wording is acceptable.

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?

Given there are no parameters and an output schema exists, the description does not need to explain return values. Still, it leaves the domain largely unexplained: what an 'interlock' is, what it means for it to be 'armed', and what kinds of safety policies are possible. The sibling names help, but the description alone is minimal rather than fully self-sufficient.

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?

This tool has zero parameters and an empty input schema, so the baseline is 4. The description adds useful meaning by explaining what the status output covers, which is all that parameter semantics could require here.

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 clearly identifies the tool as a status query reporting two specific facts: whether the interlock is armed and which safety policy is in force. It is obviously distinct from sibling tools like arm_interlock and disarm_interlock because it describes inspection rather than mutation. However, it lacks an explicit verb such as 'returns' or 'reports', so it is clear but not maximally precise.

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 description gives no guidance about when to call this tool versus alternatives such as arm_interlock or disarm_interlock. It does not state whether it should be called before changing interlock state, nor does it mention any conditions under which it should be avoided.

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?

The description implies a read-only enumeration by using 'list' and describing the output, but it does not explicitly disclose side effects, ordering, staleness, or access requirements. With no annotations, more explicit behavioral context would have been helpful, though the read-only nature is reasonably inferable.

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 concise phrase with no filler words. It is front-loaded with the core entity ('open card') and immediately lists the included attributes, making it easy to scan.

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 zero-parameter tool with an output schema, the description adequately covers what is returned and the scope ('every open card'). Some domain terms like 'open card' and 'closure limits' could be more explicit, but the output schema can fill in return-shape details, and no parameters require further explanation.

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 tool has zero parameters, so there are no parameter semantics to document. The baseline of 4 applies; the description appropriately focuses on what the returned data represents instead of parameter syntax.

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 clearly states the resource ('every open card') and the returned attributes (subunits, matrix sizes, closure limits). It avoids tautology, though it relies on the tool name for the verb and does not explicitly differentiate itself from sibling list tools like list_endpoints or list_routes.

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 is given about when to use this tool versus alternatives. With siblings such as list_endpoints, list_routes, subunit_state, and chassis_identify, the agent gets no explicit direction on when list_cards is the right choice.

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 communicates that the tool returns endpoint names and implies a read-only query, but it does not state whether any reservation or topology state is required, nor mention side effects or output behavior beyond names. This is acceptable for a simple list tool but not rich.

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, front-loaded sentence with no filler, redundant phrasing, or unnecessary detail. It states the core semantic in minimal 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?

This is a zero-parameter list tool with an output schema, so the description does not need to explain return values. It is nearly complete, but it does not explicitly connect the tool to the route-planning workflow or tell the agent when to prefer it over sibling 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?

The tool has zero parameters and the empty input schema already has 100% description coverage, so there is no parameter documentation burden. The description adds orienting context by defining what endpoints are returned, which is sufficient.

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 clearly identifies the resource returned (logical endpoint names) and scopes it to 'this topology can route between,' which also implicitly distinguishes it from sibling tools like list_cards and list_routes. However, the action 'list' is only present in the tool name, not the description, so it is slightly elliptical.

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 phrase 'can route between' implies this tool is used when an agent needs available route endpoints, likely before plan_route. But there is no explicit when-to-use guidance, no mention of alternatives, and no exclusion of cases where list_cards or list_routes would be more appropriate.

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 says the tool describes current open logical connections and does not explicitly state that it is read-only, non-destructive, or free of side effects. This is minimal but not misleading.

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 concise sentence with no filler. The most important qualifier, 'currently held open', is placed prominently and efficiently.

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 zero-parameter list tool with an output schema present, the description provides essential domain context: logically held-open connections on this server. It does not explicitly mention read-only behavior or elaborate route semantics, but those gaps are minor given the tool's simplicity and the available output schema.

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 tool has zero parameters and an empty input schema, so there is no parameter documentation burden. The baseline of 4 applies because no parameter semantics are needed.

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 identifies the resource as 'logical connections currently held open by this server', which distinguishes it from sibling tools like route_signal, plan_route, and clear_all_routes. It lacks an explicit verb like 'list' or 'retrieve', but the tool name and resource phrasing make the purpose reasonably clear.

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 is given about when to use this tool versus alternatives such as list_endpoints, plan_route, or route_signal. The phrase 'currently held open' implies it is for inspecting the current state, but there are no explicit usage conditions or 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 provided, the description carries the burden of behavioral transparency. Its use of 'List' and the planning framing make clear this is a non-mutating read operation that precedes reservation, adding useful contextual behavior beyond the tool 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?

The description is a single, front-loaded sentence. It leads with the action and resource, then gives the purpose. Every clause contributes meaning, with no filler or redundant restatement.

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?

This is a simple zero-parameter tool with an output schema, so the description does not need to explain return values. It covers what the tool does and when to call it. The only minor gap is not defining 'tier', but that is unlikely to block 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?

The tool has zero parameters, so the baseline is 4. The description correctly indicates the tool returns all tools with their tiers and adds no unnecessary parameter expectations.

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: 'List every tool with its tier'. It also explains the intended purpose ('plan before it reserves'), which separates this meta-listing tool from the action-oriented siblings like reserve_chassis or route_signal.

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 description clearly indicates when to use the tool: before making a reservation, as a planning step. It does not explicitly name alternatives or exclusion conditions, but the context is strong enough given the sibling tool set.

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 of behavioral disclosure. It explicitly states 'Nothing is switched' and frames the operation as a dry run, making the non-destructive nature and hypothetical outcome clear.

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 compact and front-loaded: it states the action, the key outputs, the safety behavior, and the recommended usage context in a few short sentences. Every sentence 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?

Despite minimal parameter descriptions, the tool context is complete: the description explains what the tool does, what it returns, that it is non-destructive, and when to invoke it. An output schema exists, so return-value details are not the description's burden.

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?

Parameter schema coverage is 0%, so the description must compensate. It does not explain how endpoints should be specified, what formats are expected, or where valid endpoint values come from. The names from_endpoint and to_endpoint are self-evident, but the description adds no parameter-level meaning beyond them.

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 uses a specific verb and resource: 'Dry run a route' and clearly states what it returns—the crosspoints that would close and whether interlocks permit it. It also distinguishes itself from switching/reservation tools by noting 'Nothing is switched.'

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 description gives an explicit usage trigger: 'Ask this before reserving the chassis.' It conveys that this is a preflight check and contrasts with actual switching, though it does not explicitly name alternative tools such as route_signal or reserve_chassis.

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. It clearly reveals three significant side effects: clearing every route, disarming the interlock, and releasing the reservation. It does not cover permissions, failure modes, or idempotency, but the core destructive behaviors are transparently listed.

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 terse sentence that front-loads the main action and enumerates the effects in a clear, ordered list. There is no filler or redundant wording; every word contributes to stating the operation.

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?

The headline effects are clear, but the description omits important operational context: when to call this versus clear_all_routes or disarm_interlock, whether a reservation must already exist, and what token means. An output schema exists, so return values need not be described, but for a compound destructive tool this is still thin.

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 only parameter, token, is required but is never mentioned in the description. Schema description coverage is 0%, so the description needed to explain what the token represents, how it relates to the reservation, or what format it expects. It provides none of 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?

The description states a concrete compound operation: clear every route, disarm the interlock, and release the reservation. This gives the tool a distinct meaning beyond its name and differentiates it from single-purpose siblings like clear_all_routes and disarm_interlock, though it does not explicitly name those alternatives.

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 explicit guidance about when to use this tool versus siblings such as clear_all_routes or disarm_interlock. The only hint is semantic: 'release the reservation' implies an end-of-life/cleanup operation, but no prerequisites, ordering, or exclusions are stated.

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 burden of behavioral disclosure. It does disclose that the reservation is time-boxed and that the returned token is a required input for mutations, which is useful. However, it does not explain what happens when the reservation expires, whether it can be renewed, or whether the reservation causes side effects beyond returning a token.

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 brief and front-loaded with the core action ('Take a time-boxed reservation'), followed by the important token detail. Both sentences earn their place, though the lack of parameter documentation limits the overall usefulness.

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?

Given two parameters with no schema descriptions and no annotations, the description is not complete enough for correct invocation. It correctly conveys the token purpose, but omits critical details about the owner and TTL semantics, reservation lifetime, and any renewal or release 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%, and the description does not explain either parameter. It never clarifies what 'owner' should be or how 'ttl_seconds' behaves beyond the default, leaving the agent to guess at required argument semantics.

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 clearly states the tool's function: taking a time-boxed reservation and returning a token required by mutating tools. It differentiates from sibling mutating tools by positioning this as a prerequisite reservation step, though it does not explicitly name the alternatives.

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 second sentence gives a clear usage signal: this tool must be called before mutating tools because it provides the required token. It does not explicitly state when not to use it, but the context of reservation-before-mutation is strongly implied.

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. 'Refused whole if unsafe' usefully discloses that the operation is all-or-nothing on safety failure, which is a non-obvious behavior. However, it does not disclose side effects, whether existing routes are affected, authentication requirements, or reversibility.

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 with no filler. The main action is front-loaded, and the second sentence adds the essential safety behavior without unnecessary 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?

The operation is a state-changing routing action with no annotations, yet the description omits prerequisites, token semantics, endpoint format, and what 'unsafe' means. An output schema exists, so return values are partially covered, but the agent still lacks key details needed to call this 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%, so the description must compensate. It clarifies that from_endpoint and o_endpoint are 'logical endpoints', but does not explain the token parameter, value formats, or any constraints. This leaves a required parameter under-specified.

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 clear action ('Connect two logical endpoints') with an explicit resource and a distinctive routing strategy ('shortest switch path'). It distinguishes itself from unroute_signal and list_routes by being the actual connection action, though it does not name a sibling.

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 or when-not-to-use guidance is provided. There is no mention of plan_route for planning, set_crosspoint for manual switching, or unroute_signal for teardown, so an agent gets no help choosing among siblings.

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 present, so the description carries the burden. It does disclose that bounds-checking and interlock-checking are 'still' applied, which is useful safety-relevant behavior, but it omits side effects, failure behavior, permissions, or what happens when the interlock is not satisfied.

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 very short, with both sentences contributing: the first states the action and scope, the second adds safety behavior. It is front-loaded and free of fluff, though it sacrifices useful 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?

Six required parameters, no annotations, and no schema descriptions demand more context than this. The tool likely interacts with interlock/reservation concepts given sibling tools like arm_interlock and reserve_chassis, but the description does not explain prerequisites or invocation context beyond noting that checks are still performed.

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 0% description coverage for 6 parameters, and the description adds no parameter-level guidance. 'One crosspoint directly' loosely maps to card/subunit/row/column, but state, token, and exact addressing semantics are left entirely to inference from parameter 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 states the tool acts on 'one crosspoint directly,' naming a specific resource and distinguishing it from route-level operations. 'Operate' is somewhat generic, but the tool name and the presence of a state parameter make the intent clear enough.

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?

'Directly' implies this is for manipulating a single crosspoint rather than using higher-level routing tools like route_signal, but it never explicitly says when to choose this over an alternative. The safety note about bounds/interlock checks gives some context but no clear 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?

No annotations are provided, so the description carries the full behavioral burden. It discloses that the output concerns 'closed' crosspoints, but it does not state whether this is a read-only query, whether it requires special access, or whether it has side effects.

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 very short with no wasted words, but it is a sentence fragment and omits a verb and key context. It is concise at the cost of under-specification.

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 with two required parameters, no annotations, and no parameter descriptions, this fragment omits the operation, parameter semantics, and any behavioral context. The output schema may cover return shape, but the calling context remains unclear.

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%, but the description only restates 'one subunit' and adds no meaning for the required card parameter. It does not explain how to identify the subunit, what card refers to, or what values are valid.

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 phrase identifies a resource—closed crosspoints on one subunit—and hints at a scope difference from crosspoint_state, but it is a noun fragment with no verb. It does not explicitly state whether the tool lists, retrieves, or summarizes that state.

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 explicit when-to-use guidance and no mention of alternatives. The word 'every' weakly implies enumeration, but the description never tells an agent when to choose this tool over crosspoint_state or set_crosspoint.

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. It does disclose the key behavioral trait of preserving crosspoints other routes still need, which is meaningful context beyond the tool name. However, it does not mention permissions, reversibility, failure behavior, or what happens to crosspoints that are no longer 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?

The description is a single, front-loaded sentence with no filler. It communicates the core action and the critical preservation constraint efficiently, making it easy for an agent to parse quickly.

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?

The description covers the primary behavior and the most important side-effect constraint, and an output schema exists so return values do not need explanation. However, given the complete lack of parameter descriptions and no usage/exclusion guidance, the agent still has significant gaps to infer before calling 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 provides no information about token, from_endpoint, or to_endpoint. The phrase 'tear down one route' does not explain how the parameters identify the route or what values are expected, so the description adds no meaningful parameter-level meaning.

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 uses a specific verb and resource: 'Tear down one route' clearly states it removes a single signal route. It also adds a distinguishing nuance—preserving crosspoints needed by other routes—which separates it from a blanket teardown like clear_all_routes.

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 description implies the tool should be used when you need to remove exactly one route while preserving still-needed crosspoints. However, it does not explicitly state when to prefer this over clear_all_routes or how it relates to route_signal, so the usage guidance is implied rather than explicit.

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 safety burden; 'Check' implies a read-only comparison and identifies the chassis report as the data source. However, it never explicitly states that no state is changed or what happens on mismatch.

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?

One short sentence, front-loaded with the verb, with no filler. Every word 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 parameterless tool with an output schema, the description covers what is checked and against what source. It does not explain when to invoke it, but the output schema handles return details, so the remaining gap is minor.

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, and the description adds no parameter details, which is appropriate. This matches the baseline for a parameterless tool.

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 names a specific action ('Check') and a concrete comparison: the topology's stored claims versus chassis-reported state. This makes the tool's role distinct from the sibling list/state tools even though no alternative is named.

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 is given; it does not say to call this after plan_route, before route_signal, or instead of chassis_identify. The need for verification is only implied by the verb 'Check'.

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