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

Annotations already declare readOnlyHint=true, and the description stays fully consistent — 'created or updated' describes the rows, not a mutation the tool performs. It adds genuinely non-obvious behavioral context the annotations do not carry: the Authorization/Bearer and x402 payment requirements, the fixed-price-per-call model, and the authoritative-source caution. This is exactly the kind of supplementary behavior disclosure the rubric asks for.

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 definition has no fluff: behavior, ordering, pagination handshake, payment, and data provenance each earn their sentence and appear in logical order. The final pair of clauses ('The official agency notice is the authoritative source' and 'source_url is authoritative') slightly repeats the same idea. At roughly 100 words it is dense but scannable rather than bloated.

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 10-parameter, read-only tool with no output schema, the description carries the weight of the non-obvious details: ordering, the change-type field, the pagination token, payment mechanics, and source reliability caveats. The schema fills in the filter semantics, so the combination covers what an agent needs for correct invocations. It does not sketch the full row shape, but with eight named parameters and this behavioral detail, the gaps are acceptable.

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 80%, so the schema carries most parameter meaning and the baseline is 3. The description surfaces the payment out-of-band metadata slot (params._meta["x402/payment"]) and the meta cursor contract, which do add information beyond the schema. It does not elaborate on the filter parameters' behavior beyond what the schema already says.

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 opens with a specific verb + resource: 'Recalls created or updated after a timestamp, oldest change first', which crisply states what the tool returns and how it is ordered. The 'change = created | updated' detail makes it easy to tell this apart from search_recalls (query-based) and get_recall (single record) without opening schemas. It stops short of explicitly naming the siblings it differs from, so differentiation is implied rather than stated.

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?

The description gives a direct usage pattern for the core flow: 'Pass meta.until as the next since', which tells an agent exactly how to paginate and loop a sync of changed records. It also provides the payment/authorization procedure, which is essential for successfully invoking this tool. However, it never says when to choose diff_since over search_recalls or get_recall, leaving that selection to inference.

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