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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's job is to add context, which it does: Market is conditionally omitted based on the caller's model_upload permission, other defaults mirror the UI, and each call yields a new request_id. That last point sits in mild tension with idempotentHint=true (repeat calls return a different identifier), but it is not a direct contradiction since no server state is described as changing.

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 short sentences, front-loaded with the return value and the retry instruction, then the conditional-omission caveat. There is no filler, though the stray indentation before the second sentence is slightly untidy.

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?

An output schema exists, so return values need no prose, and the description correctly focuses on the non-obvious bits: request_id reuse and permission-gated Market. The only gap is the missing explicit tie to research_start, which an agent must infer from the retry hint.

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?

The tool takes zero parameters, so schema coverage is trivially complete and the baseline is 4. The description adds nothing to parameter meaning because there is none to add, but it does usefully explain that output content varies by permission.

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: it returns the complete editable default plan plus a fresh request_id. The permission-conditional omission of Market further sharpens what the output contains. It falls short of 5 because it does not name a sibling (e.g. research_start) to contrast against, leaving the agent to infer the plan-then-start relationship.

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 gives one concrete usage rule: reuse the returned request_id for submission retries, which implies this tool precedes research_start. However, it never explicitly says when to call this versus research_start, research_apply_inputs, or research_precheck, and offers no exclusions or prerequisites.

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