Edifiable

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

Annotations already indicate read-only, idempotent, open-world, non-destructive behavior. The description adds meaningful behavioral detail: output distinguishes universally required pieces from terrain-triggered ones, and facts are based on commune center rather than a specific address. This exceeds annotation coverage.

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 carries the full purpose, scope, output categorization, and spatial limitation without redundancy. Every clause earns its place, and key information is front-loaded.

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 simple one-parameter, read-only tool with no output schema, the description covers purpose, scope, granularity, and categories of results. It does not enumerate the actual pieces, but that is not required for tool selection; the description is reasonably complete for invoking 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 coverage is 100%, so the baseline is 3. The description adds value by explaining that code_insee determines commune-level triggers like sismicite, risk prevention plans, and historic monuments, and clarifies spatial resolution (commune center). This goes beyond the schema's format-only 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 names a specific resource ('pieces a joindre a une demande de permis de construire pour une maison individuelle'), specifies the Cerfa form, and distinguishes universal requirements from terrain-triggered ones. This clearly differentiates it from the urbanism-rule siblings.

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 makes the context clear: it is for an individual house building permit in France, with results read at commune center, not at an address. It implicitly excludes address-level use but does not explicitly name alternatives or state when-not-to-use relative to the sibling tools.

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

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

With readOnlyHint, idempotentHint, and destructiveHint=false already covering side effects, the description adds substantial behavioral detail: it enumerates the return contents, the 120 m side-zone scope, and the equivalence to the '.md twin' of the street page. It does not discuss errors or output format, but for a read-only tool this is sufficient.

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 dense and front-loaded with the core scope, then uses a colon-separated list to enumerate return elements. Every sentence earns its place, though the first sentence is a long run-on and the reference to the '.md twin' is somewhat cryptic.

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 read-only tool with only two well-described parameters and no output schema, the description covers the returned content, the geographic scope, and the key input caveat. It is slightly incomplete in not distinguishing from sibling tools or clarifying the return format beyond 'same text as the .md twin'.

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 already documents both parameters with 100% coverage, so the baseline is 3. The description adds one valuable semantic clarification: the street number is irrelevant because the rule is read at the zone, not at the building, which prevents a likely misuse of the 'voie' 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 clearly identifies the resource (a French street and its PLU zone) and the operation's output: chapter rules, sector-specific cases, graphic-plan constraints, neighboring zones up to 120 m, prescriptions/servitudes, and triggered permit pieces. It also separates this from building-level queries by stating 'Le numero de rue est inutile : la regle se lit a la zone, pas au batiment.'

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 provides strong context for street-level PLU regulation lookup and even warns not to pass a street number, but it never names sibling alternatives such as get_french_urbanism_zone_rules or get_french_building_permit_pieces, and does not state when this tool should be preferred over them. The selection guidance is therefore 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?

The annotations already declare the tool read-only, idempotent, and non-destructive. The description adds valuable behavioral context by describing the output structure, the equivalence with the .md twin, and the failure mode where a document with unexpected numbering returns zero articles and says so instead of guessing.

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 dense but well-structured: purpose first, then output composition, then the twin-document equivalence, then the failure behavior. Every sentence adds distinct useful information 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?

With no output schema, the description adequately explains what the agent will receive: clear rules with value, condition, and regulation text, followed by full articles. It also covers an important edge case. It does not describe behavior when the commune is not compiled, but overall it is sufficiently complete for a simple two-parameter read-only 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 description coverage is 100%, with both code_insee and zone fully documented including examples and a pattern. The description adds domain context about rule categories, but no parameter-level semantic detail beyond what the schema already provides.

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 opening sentence clearly states that the tool returns what a zone of a French PLU authorizes, with a specific verb and resource. It is obviously zone-scoped and distinguishes itself from street-level or search siblings, 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?

The description implies when to use the tool: when you need zone-level urbanism rules and the commune is compiled. However, it does not explicitly contrast this tool with get_french_urbanism_rules_for_street or search_french_urbanism_regulation, so the routing guidance is left mostly 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?

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description does not need to restate safety. It adds useful behavioral detail beyond annotations: it performs keyword search over regulation text and returns the containing articles with zone and number. No contradiction with annotations.

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 carry all essential information: what the tool does, what it returns, and when to use it. The examples are compact and useful, with no redundant phrasing.

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 simple read-only search tool with two parameters, a complete schema, and rich annotations, the description is sufficient. It explains the search target, the return shape, and the typical use case. There is no output schema, so the description's mention of returned articles, zone, and number fills that gap well.

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%, with both parameters already well described. The description reinforces the meaning of 'mots' through examples but adds little semantic value beyond the schema, so the baseline of 3 is appropriate.

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 a specific verb ('Cherche des mots'), the resource (the text of a French commune's urbanism regulation), and the output (articles with their zone and number). This makes it easy to distinguish from the sibling getter tools, which target permits, street rules, or zone rules rather than full-text keyword search.

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 a clear use case: 'Utile quand on ne sait pas dans quel article une regle se trouve', followed by concrete examples like cloture, piscine, toiture, stationnement. It does not explicitly name sibling tools or state when not to use them, but the intended context is clear.

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