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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with them: it states plainly that it 'opens nothing by itself' and only returns instructions. That is exactly the non-obvious behavior an agent needs to avoid assuming the candidate is actually created after this call. It does not describe the shape/length of the returned procedure beyond 'screens, buttons, fields'.

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 the action and the critical 'returns how-to, opens nothing' correction, followed by the execution path and API rationale. The dated API/partner-terms sentence is the weakest part but still earns its place by justifying the browser-automation design.

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?

With no parameters, no output schema and full annotation coverage, the description supplies what structured fields cannot: that the return value is a procedural walkthrough and that a separate browser toolchain performs the mutation. Complete enough to call correctly; only minor gaps (return format, whether candidate details are gathered inside the procedure) remain.

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 description to disambiguate; baseline 4 applies. No parameter claims conflict with the empty schema.

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?

Names a specific verb+resource (add candidate in the user's Comeet account) and immediately qualifies it: the tool returns step-by-step guidance rather than performing the add. That qualification is essential given the misleading 'add' name, though the opening sentence still reads performatively at first glance. It is clearly separable from the cotlet_browser_* tools, which it names as the actual executors.

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?

Explicit sequencing: call this first to get the Comeet screens/buttons/fields, then execute with cotlet_browser_* in the Cloud Browser. It also explains why the official Recruiting API is not used (partner terms, sole discretion), which preempts an obvious 'why not just use the API' question. It does not address when another Comeet sibling (e.g. comeet_add_comment, comeet_list_candidates) would be the better choice.

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