Modifier une page

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, openWorldHint=true. The description adds valuable behavioral context: every change is recorded in history (listing the specific tracked fields), and push_to_cms=true sends the page to the CMS afterward. This goes beyond the annotations by explaining the side effect of history logging and the conditional CMS push. 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?

The description is a single sentence with a parenthetical list of fields and the HTTP endpoint. It's compact and front-loaded with the main action. The field list is long but necessary to convey scope. The endpoint at the end is useful context. No wasted words, though the field enumeration makes it slightly dense.

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 20-parameter mutation tool with no output schema, the description covers the main behavior (partial update, history logging, optional CMS push) but doesn't explain return values, error conditions, or prerequisites (e.g., does the page need to exist? what happens if push_to_cms fails?). The annotations cover idempotency and non-destructiveness, but the description doesn't address what the response contains or how to handle partial failures. Given the complexity, this is a moderate 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 only 35%, so the description must compensate. The description lists many field names (statut, titre, contenu, balise title, meta description, H1, slug, catégories, mot-clé, importance) but doesn't explain their formats or semantics beyond what the schema already provides. It does clarify that category_ids replaces categories and push_to_cms sends to CMS, which adds some value. However, with 20 parameters and low coverage, the description could do more to explain parameter relationships (e.g., status enum meanings are in schema, but not in 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 clearly states 'Modifier une page' (modify a page) and specifies it's a partial modification (PATCH), listing the exact fields that can be changed. It distinguishes itself from createPage and pushPageToCms by mentioning the push_to_cms behavior. However, it doesn't explicitly contrast with sibling tools like createPage or pullPageFromCms, so it's clear but not fully differentiated.

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 usage: use this to partially update a page, and if push_to_cms=true, it will also send to CMS. It mentions the HTTP method PATCH, which signals partial update semantics. It doesn't explicitly state when NOT to use it (e.g., use createPage for new pages, use pushPageToCms for pushing without editing), but the context is clear enough for an agent to infer.

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