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

Annotations already declare readOnly/idempotent/openWorld/non-destructive, so the bar is lower, yet the description adds real semantics: recruiting and not-yet-recruiting are distinct buckets, unknown local recruitment is preserved as unknown rather than inferred, and eligibility text is not an eligibility determination. Provenance (OpenRemedies, ClinicalTrials.gov) also justifies the openWorldHint. It omits defaults/pagination behavior.

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 the purpose and kept to a few short clauses, each carrying distinct information (filters, status semantics, unknown handling, eligibility caveat, provenance). The telegraphic fragment style slightly hurts readability but nothing is wasted.

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 7-parameter, no-required-params query tool with no output schema, the description covers data semantics and provenance well but never indicates what a result looks like or how limit/offset control the result set. The caveats are strong; the operational mechanics are thin.

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?

Coverage is 43%, and the description does map the five filter dimensions onto parameters, plus clarifies that status values recruiting and not_yet_recruiting are separate (useful since no enums exist). However limit and offset — two of seven parameters — get no description of meaning, default, or range anywhere.

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 the resource (registry trials) and enumerates the filter dimensions (condition/substance/status/phase/country), so an agent can tell this is a filtered search over ClinicalTrials.gov-sourced records. It does not explicitly name a sibling it competes with (e.g. get_condition_options, search_within), but the domain is unmistakable.

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?

Usage is implied by the filter list and by the 'condition_id from resolve_condition' hints in the schema, but there is no explicit 'use this when / don't use this when' or named alternative. The line about recruiting vs not-yet-recruiting is filter semantics, not selection guidance.

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