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, explicitly stating it "opens nothing by itself." It adds genuinely useful context beyond the annotations: the response shape (screens, buttons, fields) and the fact that the official Breezeway API requires a request-form key and has no MCP server. The dated API claim is extra but does not contradict anything.

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 core instruction is front-loaded and clear, but the sentence about the REST API and the "checked 20 Oct 2026" note is tangential to invoking this tool, and "from ChatGPT, Claude or any AI agent" is filler. Roughly a third of the text does not help an agent decide or call.

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 and no output schema, the description must explain the return value, and it does (step-by-step screens, buttons, fields). It also tells the agent what to do next, which is the key missing link for a guide-style tool. It could be slightly more complete by naming which browser tool starts the flow.

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 and the schema is fully closed (additionalProperties=false), so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly implies the task target is supplied later via the browser tools rather than as an argument.

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 gives a specific verb and resource ("Close task in the user's own Breezeway account") and immediately clarifies the surprising part: it returns step-by-step instructions rather than performing the close. That distinguishes it from a real action tool, though it never names the sibling that would actually close the task (cotlet_browser_close / cotlet_browser_*).

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 states the workflow clearly — call this to get the walkthrough, then execute with the cotlet_browser_* tools — which is useful sequencing guidance. However, there is no when-not guidance and no mention of the adjacent task-state tools (reopen, approve, assign) that an agent might confuse with closing, so the agent must infer the boundary itself.

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