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

Annotations only cover read-only/idempotent/open-world, while the description adds genuinely operational facts: append-only from a build-day baseline, never backfilled, capped at 25 entries newest-first, verdicts go unknown when data exceeds 9 days, failed reads return 'temporarily unavailable' rather than an empty answer, and responses stay under ~25 KB. A large share of the remaining text is policy caveat (robots-not-licence, refusal vs no-answer) that is useful context but less actionable.

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?

One enormous run-on sentence plus several dense paragraphs of disclaimers; the invocation-relevant content (since/host/kind, 25-entry cap, ordering) arrives late. Substantial material — which agencies and countries are registered, curl and urllib checks from a residential vantage, no person is named — is background that does not help an agent decide or call.

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 does cover response shape (uncertainty[], as_of, vantage, source page, notes), failure behavior, staleness and result limits — enough to call it correctly. It is complete on substance but achieves that completeness by dumping everything rather than prioritizing.

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%, so the schema already defines since, host and kind with formats and examples. The description echoes the same meaning ('a host the register covers', 'a change kind ID, such as register_created') without adding syntax or selection logic beyond the schema, which is the baseline-3 case.

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 core purpose (a change log of the Closed to Machines register, filtered by since/host/kind) is stated, but it is buried mid-way through a 200-word opening sentence dominated by register provenance detail. Nothing distinguishes it from the closely related siblings agent_access, agent_access_institution, agent_access_route or agent_access_check_url, so an agent cannot tell from the text which entry point to pick.

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?

There is no when-to-use or when-not-to-use guidance, and no sibling is named. The description explains what the register contains and what the answers look like, but never says why an agent would call this change log rather than agent_access or agent_access_institution.

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