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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description still adds real behavioral detail: per-side lists cap at 100 peers, party filter and offset page through the remainder, and peers who did not vote are omitted entirely. That last caveat prevents a serious misreading of the data. The 1-credit cost is also disclosed; only error behavior for an invalid divisionId is unaddressed.

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?

Front-loaded with what is returned, then the use-case question, then source, then pagination caveats. Dense but every clause carries information; the parenthetical credit cost is a slightly tacked-on addition but still useful. No filler.

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 carries the full burden of describing the return payload, and it does so field by field — totals, government result, party split, rebels, and per-side peer lists. Combined with the pagination and non-voter caveats, an agent has everything needed to call it and interpret results correctly.

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 3 is the baseline, but the sentence 'Lists return up to 100 peers per side, with party filter and offset for the rest' explains how limit, party, and offset interact over the same per-side lists in a way the individual schema strings do not. That interaction semantics is the added value.

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 ('Get the full result of one House of Lords vote') and then enumerates exactly what that result contains: motion/amendment text, Content and Not Content totals, government outcome, party split, rebels, and individual peer lists. The House of Lords scoping separates it cleanly from commons_division_result, and the single-division scope separates it from lords_division_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?

Gives clear context for when the tool is the right one, including the concrete question it answers ('which peers voted against the government?'). It does not explicitly state the prerequisite of calling lords_division_search first for a divisionId (that hint lives only in the schema), and it names no exclusion conditions.

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