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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so the bar is lowered; the description still adds real value by naming the source API, disclosing a cost of 1 credit, and stating the key limitation that full treaty text is not returned. It does not cover pagination or result ordering, which keeps it below 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?

Purpose is front-loaded in the first clause, followed by return fields, audience, source, limitation and cost. The long field enumeration makes the opening sentence dense, but every element carries information an agent needs.

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 enumerates the returned fields and flags the missing treaty text, and it identifies the data source. For a two-parameter keyword search this is nearly complete; only result count/pagination behavior is left implicit.

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 the baseline is 3. The description only restates keyword searching and adds no guidance on phrase handling, matching behavior, or use of the 'take' range beyond what the schema already says.

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 ('Finds treaties laid before the UK Parliament by keyword') and enumerates the returned fields (command paper number, treaty series citation, signed/laid dates, lead department, scrutiny status, debate). This is clearly distinguishable from nearby siblings such as legislation_search, statutory_instrument_search and papers_search.

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?

Names the audience and use case (trade lawyers, exporters, academics checking scrutiny under the Constitutional Reform and Governance Act 2010) and gives one explicit exclusion ('does not give treaty text beyond a GOV.UK link', implying govuk_page for full text). It stops short of naming an alternative tool or stating when a different search tool should be preferred.

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