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

Beyond the annotations, it discloses a real side-effect ('no notification is sent') and precise error semantics: 404 access_request.not_found is deliberately indistinguishable from an unknown id, and 409 access_request.not_pending applies unless pending. This is exactly the kind of behavioral detail annotations cannot carry, and it is consistent with destructiveHint=true and idempotentHint=false.

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?

Two dense sentences, zero filler; the core action and its scope come first, followed by the failure contract. Every clause earns its place.

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 guarded mutation, the description covers scope, side-effect, and error behavior, and an output schema exists so return values need not be restated. An agent has everything needed to call it correctly or avoid it.

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% for both parameters, so the description carries the burden. It never explains the 'authorization' parameter, but 'the caller's own' does constrain what access_request_id must refer to (a pending request owned by the authenticated caller), which is meaningful semantics. Partial compensation only.

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?

States a specific verb ('Withdraw') and resource ('access request') plus a scope qualifier ('the caller's own pending'). This cleanly separates it from sibling mutations such as approve_access_request, dismiss_access_request, and create_access_request without needing their schemas.

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?

It defines the calling context precisely: only the caller's own pending request can be withdrawn, with explicit failure modes (404 for other callers/unknown ids, 409 when not pending). It stops short of naming alternatives (e.g., dismiss vs. approve), so the agent must infer the routing decision.

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