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

Annotations only flag readOnlyHint=false and openWorldHint=true; the description goes far beyond by disclosing that the call creates a real lead, that the nearest independent agent receives the owner's details and may contact them, that the user is emailed a copy, and that estimates are automated comparable-based ranges with an agent-prepared fallback when no estimate is possible. These are consequential side effects the annotations cannot convey, and nothing here contradicts destructiveHint=false or idempotentHint=false.

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 purpose and the critical consent warning are front-loaded, and every sentence carries operational weight (consent, side effects, estimate nature, fallback, alternative tool). It is dense with parenthetical asides and a long em-dash clause, which costs a little readability but does not waste sentences.

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 10-parameter, 7-required mutation tool with no output schema and real-world outreach consequences, the description covers prerequisites, consent requirements, downstream effects, output nature (ranges, not formal valuations), and failure handling. The only minor omission is guidance on the condition and bathrooms inputs, which the schema already documents.

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?

Schema coverage is 40%, so the description must carry weight, and it does partially: it separates required (name, email, phone, postcode, type, bedrooms) from optional (bathrooms, house name/number) and stresses the details must be genuine. However, it never mentions the condition parameter at all and adds no format or value semantics beyond what the schema already documents for postcode, property_type, condition and house_name_number.

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 opens with a specific verb and dual resource: an automated estimate of a UK property's sale value AND monthly rent, and explicitly frames it in user-intent terms ("what is my house worth", "how much rent could I get"). It also distinguishes itself from the sibling request_valuation by naming it as the in-person alternative, so an agent can route without opening either schema.

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 explicit when-to-use intent phrases, hard prerequisites (owner's real name, email, phone, explicit agreement to be contacted), and a named alternative for the in-person case (request_valuation). It even states a when-not condition implicitly by restricting calls to genuine details with consent, which is the kind of routing guidance agents usually have to infer.

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