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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's job is to add operational context. It does: it names the upstream source (UK Parliament Statutory Instruments API), states the credit cost, and describes the coverage boundary (procedure and laying, not text). It does not discuss pagination/result-cap behaviour beyond what 'take' implies, so it stops short of fully transparent.

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?

Four sentences, front-loaded with purpose, then audience/use case, then source, then coverage boundary and cost — a logical ordering with no filler. It is slightly denser than necessary (audience sentence overlaps with the purpose), but every clause conveys real information.

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 correctly carries the return-value burden by enumerating the result fields an agent will see. For a two-parameter, read-only lookup with full annotation coverage, the only meaningful gaps are result-ordering and what an empty result means.

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 both 'q' and 'take' are already documented with types, ranges and an example. The description's 'by words in their name' restates the schema's own 'word or phrase in the instrument name, e.g. pension' rather than adding syntax, matching rules or behaviour for zero-hit queries. Baseline 3 is appropriate.

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 verb and resource ('Finds statutory instruments ... laid before the UK Parliament by words in their name') and immediately enumerates the fields returned (procedure, laying dates per House, made date, SI number). It also explicitly distinguishes itself from the regulation-text tools by pointing to legislation.gov.uk, so an agent can separate it from legislation_search and legislation_text without opening a 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?

It gives a concrete use case ('compliance and legal teams asking what regulations were just laid on a topic and how Parliament will deal with them') and an explicit exclusion ('covers laying and procedure, not the regulation text'). What it lacks is a named sibling alternative within this toolset (e.g. legislation_search / legislation_text) rather than only an external site, so the routing is clear but not fully internal.

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