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

Annotations already declare readOnly/idempotent/openWorld, and the description adds valuable behavioral context: the court filter is applied client-side during paging, `query` uses the site's own search box, and judgment text is PDF-only with nothing extracted. These details meaningfully shape how an agent should invoke and interpret results.

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?

The description is dense but every sentence earns its place: main purpose, court-filter behavior, query behavior, return fields, and the PDF-only caveat. It is front-loaded with the primary purpose and packs significant operational detail without redundancy.

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?

Despite having no output schema, the description lists exactly what each match returns (title, neutral citation, court, date, judge, PDF link) and warns that judgment text is not extracted. It also routes to get_ni_decision for full metadata. For a read-only search tool, nothing critical is missing.

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 schema already documents each parameter. The description adds meaningful nuance beyond the schema, especially for `court` (matched against citation, not a server filter) and `query` (independent of other filters). It does not add much for `year` or `limit`, but it does not need to.

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: 'Search Northern Ireland judicial decisions from judiciaryni.uk', enumerating the exact court codes and document types. It also distinguishes itself by noting that get_ni_decision provides full metadata for a single decision, so an agent can tell the two tools apart.

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?

The description gives concrete usage guidance: `court` is matched against the neutral citation/URL rather than a server-side filter, `query` is independent of `court`/`year`, and combining `court` with `year` narrows rare courts. It implies get_ni_decision as the alternative for full metadata, though it does not explicitly state 'use X when you need Y'.

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