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

With readOnlyHint already supplied, the description goes well beyond it: cursor non-advancement on read, A-to-B-to-A reversion handling, baseline-is-not-a-change semantics, absence of built-in email/ChatGPT alerts, optional signed webhook, and trial/paid key non-transfer. These are exactly the behaviors an agent cannot derive from the annotation.

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 the core purpose, then terse sentences each covering a distinct behavior, with no filler or repetition. It is dense to the point of being telegraphic, and the trial/webhook sentences sit ahead of the cursor mechanics an agent needs first.

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?

No output schema exists, and the description gives enough anchor points (digest, cursor in the return, baseline handling) to call the tool correctly. It is thinner on the actual shape of the returned digest and how changes are represented, which matters given the missing output 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 coverage is 100%, so baseline is 3, but the description adds the cursor round-trip lifecycle ('save next_cursor and send it next time') that the schema's one-line 'Last event cursor received' does not convey. It adds nothing about api_key beyond what the schema already says about preferring Bearer auth.

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 one compact chronological digest of wording changes') plus an explicit scope restriction ('ONLY your currently watched GOV.UK URLs'), which separates it from fixed_monitored_pages, page_changes and get_govuk_change_brief without needing the 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?

Gives a concrete first-call workflow ('Start since=0; save next_cursor and send it next time') and clarifies idempotent retries. It never names an alternative tool or states when not to use it, so an agent still has to infer how this differs functionally from page_changes or get_govuk_change_brief.

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