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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), but they cannot convey the non-obvious fact that a tool named 'send_a_quote' performs no side effects and returns procedural guidance instead. The description states this directly ('returns how to do it... opens nothing by itself'), plus the rationale that no member API exists, which explains why browser automation is needed.

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 critical clarification that nothing is sent appears in the second sentence, after a lead sentence that repeats the misleading name. 'from ChatGPT, Claude or any AI agent' is filler, and the final sentence restates 'official API' twice ('Checkatrade's official API: Checkatrade has an official API, but not for members'), which could be one clause.

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 annotations already carrying the safety signals, the description covers what the agent actually needs: what comes back (steps with screens/buttons/fields), that no action occurs, and which tools execute the plan. Account/auth prerequisites are only implied via 'the user's own Checkatrade account' and 'user's Checkatrade Cloud Browser'.

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?

There are zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-param tool applies. The description instead spends its words on return behavior and follow-on tooling, which is the right allocation.

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 clarifies what the name obscures: the tool does not actually send anything, it returns step-by-step instructions (screens, buttons, fields) for doing so inside Checkatrade. That distinction from acting tools is made explicit by pointing at the cotlet_browser_* tools as the executors. It does not differentiate against other adjacent siblings such as checkatrade_reply_to_a_lead or cotlet_app_guide, so a 4 rather than a 5.

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 a clear workflow: call this first to get the procedure, then execute it with cotlet_browser_* in the user's Checkatrade Cloud Browser. What's missing is an explicit exclusion or tie-break — e.g., when to prefer cotlet_app_guide over this, or whether this is required before the browser steps.

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