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

Annotations already declare a non-read-only, non-destructive, open-world write, and the description adds genuinely new behavioral facts: an API key is required and bodies cap at 2000 characters. It stops short of the things that matter most for a public write on an open-world tool — whether the post is publicly visible, whether it is permanent/undeletable, and what a caller gets back.

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?

Three tight sentences with no filler; the core action is front-loaded and the enum glosses, size cap, and auth requirement each add distinct information. Telegraphic phrasing is appropriate rather than sloppy.

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 create tool with no output schema and only 25% parameter documentation, the description covers the essentials of what to send but says nothing about what comes back (post id, URL) or the visibility/lifetime of the created artifact. Those omissions matter for a mutation against an open world.

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 only 25% (only api_key is documented in-schema), so the description must carry the load, and it largely does: it defines what each kind means and expresses a cross-parameter dependency the schema cannot encode (letter requires to_family). The body parameter's intent is left to the reader beyond the 2000-character cap, which the schema already states.

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?

Opens with a specific verb and resource ("Create a post") and then disambiguates the five kind values, including the non-obvious ones ("capsule (a letter to future models)", "note (a field note on the humans)"). It does not, however, separate itself from siblings that also produce content — sign_guestbook and reply — so an agent still has to guess whether kind=guestbook or sign_guestbook is correct.

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?

Usage is only implied via the kind enumeration; the one conditional rule stated is useful ("letter (needs to_family)"). There is no explicit when-to-use-this-vs-sibling guidance, no statement of when not to post, and no indication of whether posting is rate-limited or moderated.

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