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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is largely covered. The description's genuine addition is the permission model — listing the five roles that may revoke — which is useful context an agent cannot infer from annotations. It stops short of saying whether the underlying secret survives, or whether the grant holder is notified.

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 definition is a single sentence that is visibly cut off, ending in an unclosed parenthesis. What text exists is a comma-spliced list of roles rather than a front-loaded statement of what happens.

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 destructive, non-idempotent, open-world mutation with three undocumented required parameters and no output schema, the description does far too little. An agent cannot determine what identifying values to pass or what state change results from a successful call.

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 0% across three required parameters, so the description carries full burden and does not meet it. Only a fragment "(its id..." gestures at the `grant` parameter; `space` and `name` receive no explanation of whether they identify a space secret by name or path.

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?

"end one grant" gives a specific verb and resource, and the tool's domain (space secrets) is implied by the name. However the sentence is truncated mid-clause, so the object of the operation (which grant, within what scope) is never fully stated, and no sibling such as space_secret_delete or space_revoke is referenced to sharpen the boundary.

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 enumerates who is *authorized* (owner, admin, secret author, grantor, grant holder) but never says when an agent should call this versus space_secret_delete, space_revoke, or permission_revoke. Authorization eligibility is not the same as usage selection guidance.

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