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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the safety profile is covered. The description goes beyond that with substantive context: the ordering key (Parliament's last record update), an honest caveat that this "usually but not always reflects new parliamentary activity," the upstream source, and a 1-credit cost.

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 returned fields and the recency framing are front-loaded, and the ordering caveat and cost are appended efficiently. The audience sentence ("for public affairs teams and journalists") is mild filler but also carries usage signal, so it mostly earns its place.

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, and the description compensates by enumerating the fields returned (stage, house, dates, status). Combined with the ordering semantics, source attribution and credit cost, the agent has enough to call and interpret it; only the result count behavior is left entirely to the schema.

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% and the single `take` parameter is fully documented in the schema (integer, 1-100, default 10). The description adds nothing about it — no mention of the default page size or the maximum — so with the schema doing all the work, the baseline of 3 applies.

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 specific verb and resource ("Lists the UK Parliament bills whose records changed most recently") and enumerates the returned fields (stage, house, sitting dates, status). It clearly reads as a recency-ordered feed rather than a lookup, which separates it from bill_search or bill_status, but it never names those siblings to make the contrast explicit.

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?

"A quick 'what is moving through Parliament' view for public affairs teams and journalists" establishes the intended use case and audience, which implies when to reach for it. However, there is no explicit when-not guidance and no pointer to alternatives such as bill_search (lookup by name) or bill_status (single bill detail), so the agent must infer routing from the sibling names alone.

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