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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered. The description adds two useful behavioral facts beyond that: the corpus is limited to public trials, and results do not establish individual eligibility. It says nothing about pagination behavior (cursor/limit exist in the schema), caching/freshness semantics, or rate limits.

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 compact segments: purpose, boundary, and a concrete call example, with the purpose front-loaded. The trailing 'biomedmcp://guide' reference is terse and unexplained, spending a few characters without telling the agent what the guide contains.

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 safety profile is carried by annotations. However, for a paginated, filter-heavy search tool with 17% schema coverage, the description omits pagination guidance and the meaning of the freshness modes, leaving real gaps an agent would hit on a second call.

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 17% across six parameters, so the description must carry the load, and it largely does not. It gives meaning for 'query' and hints at the filter categories ('disease/intervention', 'status' in the example), but leaves limit, cursor, freshness, and most of the six filter keys (drug, gene, phase, source) unexplained in either place.

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 description opens with a specific verb and resource ('Find public clinical trials') and scopes the search to disease/intervention plus trial-specific filters, which distinguishes it from literature_search and other siblings. It stops short of naming a sibling it should be preferred over, so it is clear but not fully differentiated.

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 supplies a clear usage boundary ('Does not determine individual clinical eligibility'), which tells the agent this is a discovery/search tool and not an eligibility adjudicator. It offers no explicit alternative tool for eligibility questions and no when-to-use conditions relative to siblings such as study_analysis.

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