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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond that: it discloses the data source and window (27 months of appraisal-district deed dates), the exact scoring signals, weekly rebuild staleness, page size and paging mechanics, and output limitations ('individual buyers are counted, not named', 'not confirmed buyers or offers, and there are no prices'). Those caveats are exactly the context an agent needs before presenting results as leads.

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 lead sentence states purpose first, followed by scoring mechanics, output shape, paging, and caveats in a logical order with no filler. The first sentence is long and clause-heavy, but every clause carries substantive information rather than restating the name or title.

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 scoring/ranking tool with three parameters, the description covers input requirements, the scoring model, pagination behavior, staleness, linked follow-up tooling, and the epistemic limits of the output. An output schema exists, yet the description's brief mention of reason, mailing city/state, and portfolio_lead_ids is additive rather than redundant. Nothing material is missing for correct invocation.

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 description coverage is 100%, so lead_id format, page numbering, and the 1-25 limit are already fully documented in the schema. The description reinforces the paging workflow ('pass page for the next ones') and the 25-per-page cap but adds little semantic detail the schema lacks. Baseline 3 is appropriate when the schema carries the parameter burden.

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 resource: 'Rank the companies most likely to buy a Dallas County or Collin County, Texas lead.' It scopes geography, audience (investor selling/wholesaling), and the scoring basis, which clearly separates it from siblings like find_recent_buyers and find_builders_for_lot.

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 establishes the calling context ('for an investor looking for someone to sell or wholesale it to') and routes the agent onward by naming find_owner_portfolio as the consumer of portfolio_lead_ids. It does not explicitly state when to prefer this over find_recent_buyers or find_builders_for_lot, so selection against those siblings is left partly to inference.

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