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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: the upstream source (UK Parliament Commons Votes API), a publication lag of usually under an hour, a 1-credit cost, and the result field set. The only missing piece is pagination/windowing behavior beyond the take cap, which is minor for a read-only list.

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 core operation and its output shape are front-loaded in the first clause, followed by use case, source, freshness caveat, and sibling routing in descending priority. No sentence is redundant and the parenthetical cost note is compact and last, where it belongs.

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?

There is no output schema, so the description must carry the return-value burden, and it does by listing date, time, title, Aye/No totals, and the winning side. Combined with the freshness caveat and the sibling routing for deeper detail, an agent has everything needed to call this correctly and interpret the response.

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% and the single optional parameter is fully documented in the schema with its type, range 1-25, and default of 10. The description adds only the implicit notion of "latest" and "newest first" ordering, which the schema does not state but which is really result semantics rather than parameter semantics. Baseline 3 applies since the schema carries the parameter load.

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?

"List the latest House of Commons votes, newest first" names a specific verb, resource, and ordering, then enumerates the returned fields (date, time, title, Aye/No totals, winning side). It also explicitly differentiates itself from commons_division_result and lords_division_search, so an agent can pick it out of a very large sibling list without opening any 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 trigger ("what did MPs vote on today or this week?") and names two alternatives with the condition that selects each: commons_division_result for per-member names via a division_id, and lords_division_search for Lords votes. The publication-latency note also tells the agent when this tool will not yet have the data it wants.

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