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

Beyond the annotations (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description discloses the resulting state, that the call is metered at 1 request_filed, and that approval is out of scope for tools. These are exactly the facts that keep an agent from retrying or trying to self-approve.

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, front-loaded with the WRITE marker and state, then cost, then prerequisites, then the out-of-scope note. Nothing is redundant with the schema.

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 metered mutation with no output schema, the description covers the state transition, cost, and confirmation requirement. The remaining gap is per-parameter guidance and what identifier is returned, the latter being partly excused by the absence of an output schema.

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 20%, and the description only explains the confirm parameter and the reason-bearing intent; org, ttl_seconds, and especially idempotency_key (critical for a metered, non-idempotent write) are left with no meaning beyond their names. This does not compensate for the coverage gap.

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 an explicit "WRITE:" tag and a specific verb+resource (file a human sign-off request) plus the resulting state (PENDING_OWNER_SIGN), which cleanly separates it from the read-oriented siblings (get_request, list_requests, get_status). It stops short of naming a sibling for the alternative path, but the WRITE marker does the differentiation work.

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?

"Requires confirm=true" and "Granting is owner-only and is not available as a tool" tell the agent both how to invoke it and what it must not attempt afterward. There is no explicit statement of when to prefer this over checking existing requests, but the usage boundary is otherwise clear.

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