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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. With no output schema, the description earns credit by enumerating the returned fields (title, conditions, interventions/phase, derived status, sponsor, funder, dates, countries, results-posted note), though it omits what happens when the ID is unknown.

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 short sentences, purpose first, accepted formats second, return payload third. Nothing redundant and no filler.

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 one-parameter read tool with no output schema, the description covers input formats and the return payload, which is most of what an agent needs. The gap is error/not-found behavior, which is not addressed anywhere.

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 baseline is 3. The description adds value beyond the schema by explicitly listing the accepted input forms and demonstrating case-insensitive and bare-number variants ("ISRCTN12345678", "isrctn12345678", "12345678"), which the schema only states as "with or without the prefix".

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 ("look up a single ISRCTN trial by its registry number") and the word "single" implicitly separates it from a search-style sibling. It never names isrctn_search, so differentiation is inferable rather than explicit, which keeps it just below a 5.

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 "single ... by its registry number" suggests using this when an ID is already known and isrctn_search otherwise, but that alternative is never stated. No prerequisites, rate limits or failure conditions are given.

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