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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, and the description usefully reinforces that nothing is opened or submitted. However, it never addresses which lead is being replied to despite the tool taking zero parameters, which is a meaningful behavioral gap for an agent deciding whether the output applies to its case. No mention of failure conditions or what the returned steps look like when the user lacks the lead.

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 information (what you get, what it does not do, what to use next) is front-loaded in the first two clauses. The closing sentence about Zoopla's API repeats the same fact three times ('official API', 'no public API', 'no longer publicly available') and 'from ChatGPT, Claude or any AI agent' is promotional filler.

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?

There is no output schema, and the description does carry the return-value burden by stating it returns step-by-step screens, buttons and fields. Combined with the hand-off to cotlet_browser_* and the annotation-covered safety profile, an agent has enough to invoke it correctly; only the lead-targeting ambiguity remains unexplained.

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?

With zero parameters the baseline is 4, but the absence of any lead identifier is surprising for a tool named 'reply to lead' and the description never explains that the guidance returned is generic rather than lead-specific. That unstated implication costs a point even though the schema is trivially empty.

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 ('Reply to lead in the user's own Zoopla account') and immediately clarifies the actual deliverable: step-by-step instructions, not an executed reply. The key distinction from the cotlet_browser_* siblings is explicit ('opens nothing by itself'). It does not differentiate itself from zoopla_update_listing or similar Zoopla siblings, which slightly caps the score.

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?

Gives a concrete workflow: call this to get the steps, then perform them with the cotlet_browser_* tools in the Zoopla Cloud Browser. That effectively answers 'when do I use this vs. the browser tools'. It stops short of explicit exclusions or prerequisites (e.g. must a browser session already be open, must the lead exist).

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