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

Annotations only cover read-only/idempotent/open-world. The description adds real behavioral context beyond them: the full set of result states, the phase and resource_map of what was actually created, and the safety rationale (check before retrying so nothing is created twice). It also implies the tool is side-effect-free, consistent with the annotations.

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?

Front-loaded with the verb, resource, and key, and every clause carries information (field list, then the decision guidance). It is a single dense run-on sentence, so it is information-efficient but not ideally parsed.

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?

There is no output schema, so return values must be described here and they are: the result enum, phase, resource_map, error, and timestamps. Combined with the retry guidance, an agent has everything needed 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?

With one parameter at 100% schema coverage, the baseline is 3. The description adds provenance ('returned by every write tool') and ties the parameter to the retry workflow, which is slightly more than the schema's terse 'returned by a write tool'.

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 ('looks up') and resource ('a write operation') keyed on operation_id, then enumerates exactly what comes back (result states, phase, resource_map, error, timestamps). No sibling tool looks up an operation, so there is no ambiguity to resolve.

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 an explicit trigger condition: call it after a timeout, result_unknown, or partial result, before deciding to retry. It does not name a when-not or an alternative, but no plausible alternative exists among the siblings, so the gap is minor.

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