update_post

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

With no annotations provided, the description carries the full burden and does an excellent job. It discloses the two-phase confirmation flow (preview without changes, then confirmed call), the non-modifiability of the visual, the full replacement of text rather than merging, and the preservation of URN, date, and engagement. These are all behaviors beyond a generic 'update' and are clearly spelled out.

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 appropriately sized for the tool's complexity, with each sentence serving a purpose. It is front-loaded with the core action, then provides usage context, process, and constraints. Though longer than the average tool description, it is information-dense and well-structured, with no redundant 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?

Given the tool's complexity (mutation with two-phase confirmation) and no output schema, the description is remarkably complete. It explains the preview return ('retourne l'avant et l'apres'), the mandatory two-phase flow, the visual limitation, and the full-text replacement requirement. No critical aspect is missing for the agent to invoke 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?

The schema already provides 100% coverage of parameters, so baseline is 3. The description adds valuable semantic context beyond the schema: it explicitly instructs to pass the ENTIRE text ('Passe le texte ENTIER, pas un fragment') and clarifies the replacement behavior, which is not in the schema. It also reinforces the confirmed parameter's role in the two-phase flow, adding meaning beyond the schema 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 the tool's function with a specific verb and resource: 'Reecrit le texte d'un post LinkedIn DEJA publie' (rewrites the text of an already published LinkedIn post). It distinguishes from siblings by emphasizing editing over republishing and mentions preservation of URN, date, and engagement, which are unique to this update operation.

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 explicitly states when to use the tool: 'Sert quand le hook est rate ou qu'une affirmation s'avere fausse' (used when the hook is missed or a claim turns out false). It also contrasts with republishing ('editer bat republier') and explains the two-phase process similar to publish_lead_magnet, providing clear guidance and an alternative.

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