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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, non-destructive, openWorld), so the bar is lower; the description goes further by enumerating the per-result fields (time, institution, channel, direction, summary, words, snippet, source row), the single-customer scope constraint, and the verification prerequisites for agent_key. It does not mention pagination behavior even though a `cursor` parameter exists, which keeps it from a 5.

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 is front-loaded in the first clause and every sentence carries information (record scope, result shape, auth modes, query syntax). It is dense and slightly run-on, and the access_token/agent_key wording duplicates the schema descriptions, but there is little outright waste.

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 13-parameter, complex search tool with no output schema, the description does well on return shape and access modes. It still leaves more than half the filter parameters (kind, match, channel, direction, institution, date formats, limit, cursor) explained only by bare enums or not at all, which is a meaningful gap for a tool with this many knobs.

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 38% across 13 parameters, so the description must compensate. It adds real meaning for `q` (all words must appear, 'quoted words' stay together, NPI matches a clinician) and restates the access_token/agent_key semantics, but leaves `kind`, `match`, `channel`, `direction`, `institution`, `since`/`until` formats, `limit` and `cursor` undocumented beyond the enum/pattern definitions in the schema.

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 ('Search everything one customer exchanged with payers and public records') and then enumerates the exact artifact types covered (status checks, status calls/emails/replies, submissions, record changes, prior-auth updates/faxes/calls), which maps cleanly onto the `kind` enum. This is clearly distinguishable from siblings like payers_list or prior_authorization_status, which return payer or authorization state rather than the exchange history.

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 description supplies access prerequisites ('Opened by access_token ... or agent_key ...', 'one customer's records only'), which tells the agent how to scope a call, and the agent_key clause names the conditions required (verified owner email, record on in connect settings). However, it never states when to prefer this tool over alternatives (e.g. payers_list, prior_authorization_status, get_rows/get_source) or when not to use it, so routing must be inferred.

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