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

Adds substantial context beyond the annotations: validation failures create nothing and return a list of missing items, document_id overwrites the prior version, a document with a pending signature request is never modified (a new one is created instead), and an active subscription is required with no billing on refusal. Annotations confirm destructive/non-idempotent, and the description supplies the concrete consequences.

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 dense paragraph whose opening sentence front-loads what the tool does and returns. Every clause carries information, though the semicolon-chained sentences pack validation, overwrite, subscription and routing concerns together without visual separation.

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?

Covers the mutation risk, error/no-op behavior, subscription gate, sibling routing and the create-vs-overwrite branch. With an output schema present it correctly does not need to enumerate return fields, and nothing an agent needs to invoke it safely is missing.

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 schema already documents the value formats and the document_id overwrite nuance, so the baseline is 3. The description nonetheless adds a real constraint not in the schema — values must be exact and user-supplied — and cross-references get_template for field names, plus the template slug source.

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?

Starts with a specific verb+resource ('Remplit un modèle avec les valeurs fournies et enregistre le PDF'), then states the output artifacts (download link valid 24h plus the in-app document link). An agent can immediately distinguish this from siblings like get_template or get_download_link.

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?

Gives explicit routing: call get_template first to discover fields, use list_documents to retrieve an existing document. It also states the create-vs-replace branch on document_id, so the agent knows which mode it is entering and when each applies.

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, so the safety profile is covered. The description adds genuinely new behavioral facts beyond them: the 24-hour link validity and the requirement for an active RemplirPDF subscription, which is an entitlement gate the annotations cannot express.

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?

Front-loads the return value before the usage conditions, and each clause (validity, when-to-use, when-not, alternative, prerequisite) carries distinct information. It is dense and clause-heavy but not padded.

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 no explanation, and the description covers usage, the non-mutating nature, and the subscription precondition. Nothing an agent needs to invoke it correctly is missing.

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?

Only one parameter, and schema coverage is 100% – the schema already documents document_id with its doc_ prefix and its provenance (generate_document/list_documents). The description adds nothing param-specific beyond 'pour un document du compte', so the baseline 3 is right.

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: returns a new PDF download link (valid 24h) plus the in-app document link, scoped to a document of the account. It explicitly distinguishes itself from generate_document, so an agent can tell the two apart without opening 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?

Gives explicit when-to-use conditions ('quand un lien précédent a expiré', 'pour un document retrouvé avec list_documents') and a when-not clause ('ne crée ni ne modifie aucun document'), plus the named alternative generate_document for generation. Something close to a complete routing rule.

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 readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered by structured data and the 'Lecture seule : ne crée rien' clause is largely redundant. The description does add genuine behavioral value with the 'ne les inventez pas' constraint on field values and the enumeration of what the response contains, which goes beyond the 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?

Purpose is front-loaded in the first clause, followed by the return contents and then the usage rules, with no filler sentences. The parenthetical field enumeration is somewhat long but each item informs what the agent must collect from the user, so it earns its place; only slight tightening is possible.

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 document return values, yet it still summarizes them; annotations carry the safety profile; and the single required parameter is fully specified in the schema. Nothing an agent needs to select and invoke this tool correctly is missing.

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 'template' parameter already carries an enum plus a description pointing back to list_templates, so the schema does the heavy lifting. The description reinforces slug provenance but adds no format, casing, or validity detail beyond what the schema provides; 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 specific verb and resource ('Décrit un modèle') and then enumerates the exact contents returned: fillable fields with their attributes, auto-computed fields, and signatories. This lets an agent distinguish it immediately from list_templates (which only lists) and generate_document (which produces the document).

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?

Explicitly states the sequencing rule ('À appeler avant generate_document') and the reason ('pour savoir quelles informations demander à l'utilisateur'), plus a negative instruction not to fabricate values. It also routes the agent to list_templates for slug discovery, naming the alternative and the condition that selects 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?

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the closing sentence 'Lecture seule : ne crée ni ne modifie rien' largely restates structured data. What it does add beyond annotations is the ordering guarantee (most recent first) and the returned field list, but no pagination limits, account scoping caveats, or failure modes are covered.

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 resource and scope, followed by the routing guidance. Slightly wasteful only in the trailing read-only sentence, which duplicates the annotation hints.

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 listing tool with an output schema present, everything an agent needs is covered: what it returns, ordering, and which sibling to call next. The field enumeration mildly duplicates the output schema but leaves no functional gap.

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% and the single 'limit' parameter is fully documented in the schema with default and 1-50 bounds, so the description reasonably leaves it alone. Baseline 3 applies since the description adds no syntax or semantics beyond the 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?

States a specific verb (Liste) and resource (documents de location générés dans le compte) plus the fields returned and the sort order (du plus récent au plus ancien). This clearly separates it from get_download_link and generate_document, which the description explicitly names.

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?

Gives explicit downstream routing: use it to retrieve a document_id before calling get_download_link, or before updating a document with generate_document. That is a concrete when-to-use condition tied to named sibling tools, not an implied one.

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 readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; the closing 'Lecture seule : ne crée rien' largely restates that. It does add useful non-annotation context: results are paginated one template per catalog page. No auth or rate-limit detail, but the bar is lower with annotations present.

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?

Front-loaded with the purpose and the routing rule before the long parenthetical catalog list. The enumeration of a dozen template types is somewhat verbose, but it is informative and the sentence still 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?

An output schema exists, so return values need no explanation, and the description still names the key fields. For a zero-parameter, read-only list tool the definition covers everything an agent needs to select and 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline is 4. The mention of slug/catégorie/signataires describes output fields rather than inputs, which is harmless.

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 ('Liste les modèles de documents de location français') and enumerates the catalog contents (bail meublé, bail vide, quittance, etc.) with the fields returned (slug, catégorie, signataires). It explicitly distinguishes itself from the sibling get_template, so an agent can tell the two apart without opening a schema.

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?

Gives an explicit routing rule: call this first when the template slug is unknown, and use get_template instead for the fields of a specific template. The when-to-use and the named alternative are both present, leaving nothing to inference.

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