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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent write, and the description adds substantial context beyond that: the wall is public and anonymous by default, only industry is derived from the workspace profile, show_name=true reveals the nickname, requests are moderated, the factory triages daily and replies publicly, the user is notified on status change, and the return value is a public URL. That is genuinely rich disclosure. However, it never states the privacy/user-identity consequence of improving someone else's template or what happens to a request that fails moderation, so it is strong but not exhaustive. Because annotations carry the safety profile and the description adds real behavioral context, a 3 sits appropriately between 'adequate' and 'rich'.

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?

Dense but front-loaded: purpose first, then when-to-use, then content rules, then rate limits and outcome, then the return value. Every sentence carries information, though the middle section on text content and privacy is packed into one long clause-heavy sentence that is harder to skim.

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 correctly states what is returned (the request's public URL) and to show it to the user, and it covers the consent, anonymity, and moderation flow an agent needs before calling. The gap is the internal inconsistency between the schema's maxLength of 1000 and its own note of 'up to 500 characters', which the description does not resolve.

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%, so the baseline is 3, and the description earns an increment by explaining that template_key must be the key from list_examples, that show_name should only be passed with user consent, and by giving content guidance for text (say what they want, who reads it and where). It stops short of addressing scene or the 1000-vs-500 character discrepancy, leaving some ambiguity.

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 opens with a specific verb+resource: 'Post a request on LivePage's public template request wall', and immediately disambiguates the two modes (kind=new vs kind=improve). It also ties the tool to its sibling, naming list_examples as the source of template_key and the trigger for using this tool, so an agent can distinguish it from sibling 'report_task' or 'send_feedback_to_livepage' 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?

Explicit when-to-use conditions are given: only when list_examples has nothing that fits, or a template lacks something needed, and only after the user agrees to submit. It also names the alternative (list_examples) and the gate (user consent), plus the per-day cap and moderation step that constrain invocation.

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