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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description still adds genuinely new behavior: result cardinality capped at five per page, that entries are 'sourced' and surface conflicts and verification gaps, and that no contact or patient data is returned and no leads are created or delivered.

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?

Three tight sentences, front-loaded with scope before caveats and pagination; no filler. The only blemish is the undefined 'next_offset' term, which costs a bit of precision in an otherwise efficient block.

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 seven-parameter tool with no output schema, the description does well on return shape (up to five sourced candidates, conflicts and gaps disclosed) and exclusions. It falls short on the optional filters (must_have, deployment, budget), whose semantics live only partly in the schema.

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 only 29%, so the description carries extra burden. It reinforces the specialty and clinician-count constraints and explains page size, but says nothing about must_have, deployment, or monthly_budget_usd, and it renames offset as 'next_offset' rather than clarifying offset semantics.

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 first sentence names a specific verb (research/find), resource (EMRs), and hard scope (US primary-care or behavioral-health practices with 1–10 clinicians), so an agent can tell this is discovery rather than vendor lookup. It does not explicitly name the sibling it is distinguished from (compare_emr_options), leaving that inference to the 'candidates, not suitability guarantees' phrasing.

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 sets a clear use condition (small practices in the two named specialties) and boundary exclusions (no contact details, no patient data, does not create or deliver leads), which is real guidance. However, it never routes the agent to compare_emr_options or get_emr_evidence for the follow-up step, and the pagination hint references 'next_offset', a name that does not exist in the schema.

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