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

Annotations already mark it read-only and idempotent; the description adds useful behavior beyond that: it tolerates arbitrary PL number formatting, groups results by document type, and returns authoritative PDF URLs rather than a summary. It also discloses a limitation (indication text lives inside the SmPC PDF, not in this register), which helps an agent set expectations. No contradiction with annotations.

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 opens with the main resource and grouping, then input flexibility, then output and a caveat, with no wasted words. Every sentence contributes distinct information. It is longer than a one-liner, but the length is earned.

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 one required parameter, no output schema, and read-only annotations, the description covers the essential call context: what you pass in, how the input may vary, what you get back (PDF URLs), and a key limitation. An agent has enough to invoke this correctly without further inference.

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?

The schema already documents pl_number with an example and 100% coverage, so the baseline is 3. The description adds value by stating that any spelling of the PL number is accepted and supplying additional forms ('PLGB', 'PLNI'), which the schema example does not fully convey. That extra input-format guidance justifies a 4.

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 names a concrete resource ('every MHRA document held for one UK licence number') and an explicit output ('Returns the authoritative PDF URL for each'), grouped by document type. It also clarifies what the tool is not ('not a summary'), which separates it from a generic search tool. This is far more specific than the title 'Mhra Product' alone.

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 clearly implies the tool is for looking up all regulatory documents tied to a single PL number, including the SmPC, leaflet, and PAR, while noting it should not be used when you need the indication text itself. It stops short of naming sibling tools like mhra_search or mhra_recent_changes or giving an explicit 'use this when...' rule, so there is clear context but no formal exclusions.

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