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

With no annotations, the description carries the full behavioral burden and does so: daily refresh cadence, a hard 90-day history limit, newest-first ordering, and a per-call cost of 1 credit. These are exactly the constraints an agent needs before committing to a polling strategy.

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?

Dense but every clause earns its place — source list, semantics, rationale, filter syntax with example, and cost, all front-loaded with no filler. Long but not padded.

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?

For a 6-param, nested-object tool with no annotations and no output schema, the description covers source semantics, the filter contract, history window, ordering and cost. It doesn't describe the shape of returned rows or pagination behavior (page/per_page defaults), which is the main remaining gap given there's no 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 description coverage is only 17%, but the description compensates for the hardest parameter by explaining that `filter` takes the source's own query params (pointing to list_sources supported_params, plus q) and gives a concrete example. `since`, `page`, `per_page` and `change` are left to the schema, which is mostly self-evident from names, enums and defaults.

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 ('rows added, removed or changed between daily refreshes of a register dataset') and enumerates the exact sources covered. It also distinguishes itself from the query_* siblings by declaring itself a polling tool rather than a full re-read.

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?

Explicitly routes the agent: 'Poll this instead of re-reading a whole register,' which names the alternative class of tools (query_*) and the condition for choosing this one. It doesn't state when not to use it (e.g. backfill beyond the 90-day window), so it falls short of full when/when-not coverage.

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