Callejear France

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely non-obvious behavior: streets in the same IRIS yield identical data, and no quantified difference is returned when source dates don't allow verified temporal comparison. These are real disclosure of output behavior beyond the annotations, though the telegraphic phrasing makes them slightly hard to parse.

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 three telegraphic fragments are short and front-load the count constraint, but the compression tips into ambiguity — "sans gagnant" and the temporal-comparison clause require interpretation rather than being crisp statements. Dense but not optimally structured.

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?

An output schema exists so return values need not be explained, but for a comparison tool with an undocumented dimensions parameter and no routing guidance versus callejear_get_street_context, the description leaves important gaps. The cryptic fragments do not fully prepare an agent to call it correctly.

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

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

Schema description coverage is 0%, so the description must carry the parameter burden. "Deux à cinq rues" merely restates the street_ids minItems/maxItems already enforced by the schema, and the optional "dimensions" parameter is not mentioned at all, leaving its enum semantics 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?

The description conveys the resource ("Deux à cinq rues") and a key scope constraint ("sans gagnant"), but never states a clear verb like "comparer" — the action is only inferable from the tool name. It does not explicitly distinguish itself from the sibling callejear_get_street_context, leaving the comparison intent 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 a hint of the operating constraint (2-5 streets) and a caveat that no numeric difference is shown when source dates don't permit a verified temporal comparison, but no explicit when-to-use or when-not-to-use versus siblings like get_street_context or get_coverage. The agent must infer the selection context.

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?

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds a meaningful epistemic caveat (catalogue counts do not prove publication or indexing), which is useful beyond the annotations, but it omits auth requirements, rate limits, or pagination 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?

Two short sentences with no filler; the catalogue scope is front-loaded and the caveat follows efficiently. It is appropriately sized, though the second sentence is slightly opaque and could be clearer without adding length.

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?

An output schema exists, so return values need not be explained. However, the description still omits the tool's actual output semantics, how city_id affects coverage, and when to prefer it over sibling tools, leaving the agent under-informed for 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%, and the single optional city_id parameter is never mentioned in the description. An agent cannot learn from the description what city_id does, what happens when it is omitted, or that it expects a French postal code pattern.

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 domain (national catalogue of Callejear.fr and source limits) but uses a noun phrase rather than a clear verb+resource. It does not state what the tool actually returns (coverage counts, list of covered communes, etc.) and gives no basis for distinguishing it from siblings like search_communes.

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

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

There is no when-to-use guidance, no mention of alternatives, and no conditions that select this tool over the sibling search/compare tools. The caveat about counts not proving publication is a data-quality note, not usage direction.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description nevertheless adds real behavioural context by ruling out radius searches and housing-risk metrics, and by flagging that source text is data and never instructions — a meaningful prompt-injection safeguard for a tool returning scraped municipal data.

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 with no filler; the payload description is front-loaded and the caveats follow. The injection warning, while valuable, is dropped in without a framing sentence, making the block read as terse fragments rather than structured 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 an output schema present the description needn't explain return values, and annotations carry the safety profile, so the main omissions are input semantics and routing guidance. For a two-parameter, enum-bearing tool with zero schema descriptions, those gaps keep it at minimum-viable rather than complete.

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 compensates for none of it: street_id's 'fr:' identifier format and the dimensions enum values (services.health, services.education, etc.) are never explained. Naming IRIS and GASPAR describes output content, not the inputs, so the agent learns nothing new about how to populate either parameter.

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 the exact payload: BPE facilities for the IRIS statistical neighbourhood plus GASPAR codes for the commune, which is more specific than the vague title 'Contexte territorial d'une rue'. It does not, however, contrast itself against siblings like callejear_get_coverage or callejear_compare_streets, so the boundary is left for the agent to infer.

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 statement, no prerequisites, and no alternative named. The exclusion 'Aucun rayon' hints at scope but never tells the agent which sibling to prefer when a radius-based or coverage query is actually wanted.

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?

Annotations already declare this as a read-only, idempotent, non-destructive, closed-world lookup, so the safety profile is covered. The description usefully adds that homonyms are disambiguated by département and that historical local names are indexed, but says nothing about pagination or result limits despite the cursor/limit params.

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, front-loaded sentences with no filler; the primary instruction (find the INSEE code first) leads. Telegraphic style leaves a little ambiguity but is appropriately sized.

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?

An output schema exists, so return values need not be explained. However, with zero parameter documentation and no pagination guidance for a search tool, the definition is only marginally complete 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% across all three parameters. The description hints that the query concerns commune names, but never explains the query string semantics, the limit/cursor pagination pair, or how the INSEE code is returned. It fails to compensate for the empty schema.

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

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

The description states a specific verb+resource: finding the INSEE commune code. It implicitly distinguishes itself from callejear_search_streets by framing itself as the prerequisite step, though it never names the sibling directly.

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?

'Trouver le code INSEE avant de chercher une rue' gives clear sequencing guidance — call this before a street search. It stops short of naming the alternative tool or stating when not to use it.

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 readOnly/idempotent/non-destructive covered by annotations, the description still earns credit for disclosing provenance and a reliability caveat: links come from a local manifest "sans garantie de disponibilité actuelle," and results are unranked residentially. That is real behavioral context beyond the annotations, though it omits anything about 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?

Two compact sentences, front-loaded with the core purpose and scope before the caveat. No filler, though the density of the second clause is a minor readability cost.

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?

An output schema exists, so return values need not be described. However, for a 4-parameter tool with zero schema descriptions, the description leaves limit and cursor semantics entirely unexplained, so it is not fully complete despite the useful provenance note.

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

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

Schema description coverage is 0% across 4 parameters, so the description must carry the full burden. It only clarifies that city_id is an INSEE code; query, limit (max 20), and cursor (pagination) receive no explanation, leaving the majority of 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 ("Recherche textuelle") and resource (streets) scoped to a single commune, and adds the negative constraint "pas de classement résidentiel." This distinguishes it from the sibling callejear_search_communes by resource, though it never names that sibling explicitly.

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 "dans une seule commune identifiée par son code INSEE" implies the tool is limited to one municipality at a time, which is useful scoping, but there is no explicit when-to-use vs. when-not guidance or mention of the sibling alternatives (compare_streets, get_street_context, search_communes).

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