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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, yet the description still adds real behavioral context: only the best match per name is returned, output is compact with a summary count, and the no_match_after_filters case returns the best record excluded by the filter rather than an empty result. That last detail materially changes how an agent should interpret results and is not derivable from the annotations.

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?

Purpose and batching scope are front-loaded in the first clause, followed by return-shape and edge-case details. It is dense but every clause carries information; the only slightly wasteful element is the parenthetical asides, which could be tightened without losing meaning.

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 output schema, the description must carry the return contract, and it does: best match per name, compact form, summary count, and the no_match_after_filters shape. It stops short of naming the fields returned for a match (e.g. score, matched name, address), which would be useful for a tool whose whole output is matches, but the essentials are present.

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 every parameter including min_score's default and 1.0 semantics and the per-entry state/npi/dob override rule is already documented in the schema. The description restates the name-or-object entry shape and the YYYY-MM-DD dob format without adding syntax or behavior beyond what the schema provides, so the baseline of 3 applies.

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 (screens), a specific resource (person or business names against the LEIE), a batch limit (up to 25), and the distinguishing behavior (returns only the best match per name rather than all candidates). It also positions itself against the sibling screen_exclusion by noting it uses the same LEIE mirror, so an agent can tell the batch tool from the single-name tool.

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?

The 'up to 25 names in one call' framing makes the batch use case clear, and the reference to screen_exclusion establishes the relationship between the two. However, it never explicitly says 'use this instead of screen_exclusion when you have multiple names,' nor does it state a precondition such as a requirement for one name only below the batch limit.

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