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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuine context beyond that: output is one compact JSON row per trial with a link to the source record, and there is a per-result price of $0.004 per trial, which matters for an agent deciding how to size maxResults. It does not disclose pagination or rate-limit behavior, keeping it short of 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?

Two tight sentences plus a one-line price note, with the capability and output shape front-loaded before the audience framing. The audience sentence ('Built for AI agents and people in pharma, biotech...') is the weakest part and borders on filler, but the whole thing stays short.

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 14-parameter, no-output-schema tool the description does the heavy lifting on return values — listing the dossier fields and the per-row link — and adds cost. The main gap is the `detail: full` mode, which the schema barely explains and the description never mentions, so an agent cannot judge what the richer payload contains.

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 one of the 14 parameters is already documented with examples and formats, making 3 the baseline. The description's field list loosely echoes the filter set (phase, status, sponsor, conditions, drugs, dates, countries) but adds no syntax, matching behavior, or interaction rules beyond what the schema provides.

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 states a specific resource (ClinicalTrials.gov trials) and two capabilities — searching by criteria ('which trials?') and pulling a per-trial dossier by NCT ID ('where does this trial stand?') — and enumerates the returned fields (status, phase, sponsor, enrollment, dates, countries, outcomes, results-posted flag). It is clearly distinguishable from siblings like drug_safety or sec_filings_feed, though it never names an alternative to contrast with.

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 only implied: the phrase 'which trials?' hints at filter-based search and 'where does this trial stand?' hints at single-trial lookup via nctIds, but the description never explicitly says when to use one mode versus the other, nor when this tool is preferred over a sibling such as drug_safety. The only explicit mode reference ('search mode') appears in the schema, not the description.

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