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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds real value beyond that: it discloses the authorization requirement (capability, not just ID), the security constraint (never reveal it publicly), and the scope limit (metadata approval cannot execute or publish).

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?

Four short sentences, front-loaded with purpose followed by the authorization caveat. Each sentence carries an operative constraint; the 'metadata approval cannot execute or publish' line is slightly tangential but still bounds what this read grants.

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 should convey what is actually returned (proposal fields, status values), which it never does. Annotations cover safety and security is well handled, but an agent cannot anticipate the response shape from this text.

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 50% – creator_capability is documented in the schema, submission_id is not. The description compensates by clarifying that the submission_id identifies the record but is not itself authorization, and by characterizing the capability as a private secret, adding meaning beyond the regex pattern.

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 verb 'Read' plus the resource 'your private proposal/status' states what the tool does, and the 'atbc_ capability' framing makes clear it is a credentialed self-lookup. It does not, however, explicitly distinguish itself from siblings like get_product or get_review, leaving a small gap.

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 line 'A submission ID alone is not authorization' implies you must supply the original capability, and the call is clearly scoped to 'your' submission. But there is no explicit when-to-use guidance, no statement of when this is preferable to other read tools, and no mention of failure modes if the capability is wrong.

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