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

Annotations already cover the safety profile (read-only, idempotent), and the description adds genuinely non-obvious behavior on top: condition+intervention is an AND not an OR, a zero result is a real zero rather than a silent failure and is reported explicitly, and `status` is client-side over a derived field because ISRCTN's feed has no status. That is exactly the kind of context an agent cannot infer 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 the identity of the registry, then use cases, then the constraint, then the semantic traps. Dense but nearly every clause carries information; the final `status` sentence is the longest and could be trimmed slightly, but it is not padding.

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?

With no output schema, the description usefully names two response fields (`status_basis`, `status_filter_scanned`) so the agent knows what comes back. Minor gap: nothing about result-count/truncation behavior beyond the schema's limit, and no mention that zero results are reported rather than erroring at the limit boundary.

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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: multi-word query terms are ANDed, combining condition and intervention is an AND, and `status` matches a derived value exposing `status_basis` per trial. It does not restate ranges such as limit 1-50, which the schema already carries.

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 the ISRCTN registry of clinical trials) and immediately scopes it against the obvious alternative registry, ClinicalTrials.gov. An agent can tell this apart from sibling isrctn_trial (single-trial lookup) and from generic web search without opening the schema.

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?

Gives concrete use cases ("trials of psilocybin for depression") and an explicit routing rule: use this for UK/international trials not necessarily registered on ClinicalTrials.gov. It also states the hard precondition that at least one of query/condition/intervention is required. It stops short of naming the sibling isrctn_trial as the follow-up for a specific trial ID.

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