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

Annotations already cover read-only/idempotent/non-destructive, and the description adds the non-obvious behavioral fact that it 'opens nothing by itself' — i.e., it is advisory text only, not an actual fetch. It also discloses the external dependency on a workspace-scoped API key from Recruiterflow support. It falls short of describing what the returned instruction text actually looks like or how long/detailed it is.

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?

The operative facts (returns steps, opens nothing, then use cotlet_browser_*) are front-loaded and the API caveat is appended as a secondary note. Minor waste in the opener ('from ChatGPT, Claude or any AI agent') and the oddly dated parenthetical, but nothing that obscures the core instruction.

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 zero-parameter, no-output-schema guidance tool, the definition covers what it returns (step-by-step UI instructions), that it performs no action itself, and which tools execute the action. The only gap is the shape/format of the returned instructions, which is a small omission given the tool's simplicity.

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 there is nothing for the schema to explain and nothing for the description to compensate for. Baseline 4 applies; the description does not wrongly imply any filtering or scoping inputs.

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 states a specific action and resource, but crucially reframes it: the tool does not return job data, it 'returns how to do it in Recruiterflow step by step (screens, buttons, fields)'. That corrects an expectation set by the name 'list_jobs' and makes the tool's real purpose unambiguous, though it does not name any sibling Recruiterflow tool it competes with.

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?

Clear handoff guidance: after getting the steps, 'then do it with the cotlet_browser_* tools in the user's Recruiterflow Cloud Browser', and the API note explains why the direct route is unavailable (keys are not self-serve). It gives the when and the what-next, but no explicit 'do not use this if' exclusion.

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