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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the bar is lower, yet the description still adds real operational context: a Last Price credential with audit read scope is required, and a sandbox key from self-registration is refused with 403 until a human claims the workspace. That pre-empts the most likely failure mode for an agent.

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 sentences, front-loaded with what is returned, then id provenance, then gating prerequisites. Every sentence earns its place and nothing is repeated from the schema or annotations.

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?

No output schema, but the description compensates by naming the fields returned (action, requester, status, reason, decision timestamp). Combined with the auth/workspace preconditions, an agent has everything needed to call this correctly and to interpret a 403.

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 100% and the single parameter is already documented as "the approval id, as list_approvals gives it." The description's provenance note ("or the notification that announced it") adds only a marginal source hint beyond the schema, so the baseline 3 applies.

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 ("Read one approval") and enumerates the content an agent will get back: the held action, requester, status, reason, decision time. That distinguishes it cleanly from list_approvals (many, summarized) and decide_approval (mutates state), so no schema inspection is needed to disambiguate.

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 retrieval context – the id comes "from list_approvals or the notification that announced it" – which tells the agent how this tool chains after a listing or notification call. It stops short of explicitly ruling out alternatives (e.g. use list_approvals when you don't yet have an id), so it is strong but not fully routing.

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