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

The readOnlyHint annotation already establishes the read-only profile, and the description correctly adds the idempotency purpose. However, it does not disclose the failure mode (what happens when no request matches the key) or the scope of the lookup (whether project_id narrows it). These are exactly the behaviors an agent needs when retrying.

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?

A single efficient sentence with no filler, and the return behavior is front-loaded. The phrasing is slightly indirect but nothing is wasted.

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 two-parameter lookup with no output schema and no parameter documentation, the description should state what is returned and what happens on a miss. It covers only the motive (idempotency), not the mechanics an agent needs to call it correctly.

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%, so the description must carry the parameter meaning. It mentions 'idempotency_key' rather than the actual 'request_key' parameter and says nothing about 'project_id', leaving both parameters effectively undefined.

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?

The description says it returns previously started work keyed by an idempotency key, which is a specific concept. But it never names the resource (a capacity request) and refers to 'idempotency_key' while the actual parameter is 'request_key', so an agent must infer the mapping. It is not clearly distinguished from siblings such as get_capacity_execution or get_capacity_quote.

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 retry framing implies the usage context: call this after a retry to check whether work was already started. No explicit when-not or named alternatives are given, and it does not explain what to do with the result versus calling authorize_capacity_work.

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