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

Adds substantial context beyond annotations: no idempotencyKey, never resends an already-sent notification, creates no review, and the non-deterministic failure mode where a lost delivery acknowledgement produces an uncertain result. This is exactly the behavioral detail the non-idempotent annotation alone would not convey.

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 action and immediately followed by the key constraints and the recovery path. No filler or restatement of the title.

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 non-idempotent mutation with no output schema, it covers the critical gaps: what it does not affect (no review created), its no-double-send guarantee, and how to verify the result via company_get_post_approval. An agent has everything needed to invoke it safely.

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 100% and both parameters are fully documented in the schema (exact IDs, never a personal platformId). The description adds no parameter-level syntax or format detail, so it earns only the baseline for a well-documented two-param schema.

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 and resource ('Retry the client-decision notification') plus the recipient ('requesting manager'), which is enough to distinguish it from adjacent approval tools like company_request_post_approval and company_resend_invitation. It also pre-empts confusion by noting it 'Creates no review'.

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?

Gives clear operative guidance: inspect notificationStatus via company_get_post_approval afterward, and warns 'do not retry blindly' because a lost acknowledgement leaves an uncertain outcome. It names the follow-up alternative but does not explicitly contrast this with other approval-related siblings an agent might pick.

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