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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses a privacy contract ('send only the schema's bounded categories; never send names, identifiers, record text, or uploaded documents'), deterministic hold behavior for missing routing facts and unsupported routes, and the fact that it reuses an existing preparation kit. These are non-obvious behavioral traits the agent cannot get from structured fields.

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?

Front-loaded with what the tool produces, followed by exclusions and privacy constraints; every sentence carries information. It is dense but not padded, though the long single-paragraph negation run is slightly harder to scan than a split scope/limits structure.

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?

An output schema exists, so return values need not be described, and the description covers scope, privacy, and hold semantics for a complex 12-parameter tool. The remaining gap is that most enum parameters lack meaning guidance, leaving the agent to guess correct values for routing facts such as regulatory_state_basis.

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?

With only 25% schema description coverage across 12 parameters, most fields (program, appeal_stage, denial_reason, employer_type, funding_status, regulatory_marker, regulatory_state_basis) are unexplained in both schema and description. The description does clarify the key contract that only bounded categories may be passed and that record contents are out of scope, but it never explains individual routing facts or how they map to checklist output.

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: 'Prepare a free, category-level evidence checklist for a knee osteoarthritis hyaluronic-acid injection denial,' plus the inputs it consumes (routing facts, injection-series status, record availability categories). No sibling tool in the list produces a checklist, so the agent can immediately separate it from the get_*/list_* lookup tools.

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 gives strong context for when this applies (a knee OA HA injection denial) and enumerates explicit exclusions: it does not inspect records, verify insurer criteria, give clinical recommendations, draft an appeal, calculate deadlines, or estimate success. It does not name an alternative tool for those excluded needs, so the agent must infer where to go instead.

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