plugtrip

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

readOnlyHint=true already covers the safety profile, so the bar is lower. The description usefully adds that the tool is free of charge, but it says nothing about what the response contains (feature catalogue vs. live data) or its size, which is the main behavioral question for a discovery call.

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 sentence that leads with the verb and enumerates scope, with no filler. It is slightly padded by the vague qualifier 'réelles' and the trailing 'Gratuit.'

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 parameters, no output schema, and an annotated read-only hint, the definition is nearly adequate. Still missing is a minimal indication of what the agent gets back (a list of capabilities) that would let it decide whether to call this before or after the 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 takes zero parameters, so there is nothing for the description to disambiguate. 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?

The verb 'Découvrir' and the resource 'fonctionnalités de Plugtrip' are stated, and the enumerated domains (recharge, pauses, trajet, logement, communauté, véhicules) hint at scope. However, 'fonctionnalités réelles' is vague about what the tool actually returns — a feature list, documentation, or a capability check — and it does not explicitly separate itself from the sibling search/context tools.

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 call this instead of search_stations or station_context, nor any prerequisite or exclusion. 'Gratuit' signals cost but says nothing about selection conditions.

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?

It discloses traits not present in the annotations: a 0,01 EUR charge per useful response, no billing on failure or empty result, an Authorization-header API key requirement, and stable request_id for retries. This also explains why a search tool carries readOnlyHint=false – billing is a side effect. It stops short of describing result shape or pagination.

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 clauses, front-loaded with the purpose, then cost terms, then auth and retry mechanics. No filler, though the pricing sentence could tie more directly to the max_cost_cents parameter.

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 6-parameter tool with no output schema and zero schema descriptions, the description covers billing, auth and idempotency well, but omits spatial-search semantics (radius, limit caps) and the meaning of the cost cap parameter. Adequate for operation, incomplete 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%, so the description must compensate and largely does not. It only explains request_id ('stable pour les reprises'), leaving latitude, longitude, radius_km, limit and especially the required max_cost_cents (presumably the cost ceiling tied to the 0,01 EUR pricing) undocumented anywhere.

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 ('Rechercher des stations') plus a hint of payload ('leur contexte documenté'), which separates it loosely from discover_plugtrip. However, it does not distinguish itself from the sibling station_context, despite the phrase 'contexte documenté' suggesting overlapping territory.

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 when-to-use or when-not-to-use guidance and never names station_context or discover_plugtrip as alternatives. The retry/failure notes are operational rather than selection 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?

The description adds real context beyond the annotations: a per-response cost of 0.02 EUR and a rule that availability must never be invented, which tells the agent the answer is authoritative and billable. It does not explain why readOnlyHint is false for a "read", nor what a "useful answer" versus a failure looks like.

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 action and immediately followed by the cost/no-fabrication constraint. Nothing is padded, though the terseness is part of why key information is missing.

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 three-required-parameter, zero-coverage, no-output-schema tool that also charges money, the definition is thin: no explanation of request_id's role, the budget ceiling, what fields a "fiche" returns, or what a failed/invalid lookup costs.

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 carry parameter meaning and it does not: station_id, request_id (likely an idempotency key given the 8-128 char constraint) and max_cost_cents are never mentioned. The cost sentence hints at a budget cap but gives no relation to max_cost_cents.

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 gives a verb and a vague resource ("Lire une fiche") but never says the fiche is a station record, even though the tool name is station_context and siblings are search_stations/discover_plugtrip. An agent can infer it fetches station detail, but the description itself leaves the mapping implicit.

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 call this instead of search_stations, nor any prerequisite (e.g. call after a search, or that a paid lookup requires a budget). Usage must be inferred from the tool name alone.

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