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

No annotations, but the description handles the burden: discloses return shape (recalls plus changed_count and new next_cursor), cursor stability across restarts, bootstrap behavior, and cost/HTTP details ($0.005 via x402, GET endpoint). Does not spell out pagination limits but covers most behavioral traits.

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 meaning and scoping, dense but each sentence adds a distinct fact. The bracketed HTTP metadata is slightly noisy but useful; no real waste.

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 single-param, no-output-schema delta endpoint, it covers purpose, bootstrap, cursor stability, return fields, sibling routing, and access/cost. Nothing an agent needs to call it correctly is missing.

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?

Single parameter with 100% schema coverage (baseline 3), and the description adds value beyond schema: how to source the value (next_cursor from last call) and the bootstrap-once behavior when omitted.

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 the specific verb/resource ('product recalls changed since your cursor') and disambiguates from the full listing ('delta of /v1/recalls'). Distinguishes from siblings like gov_recalls and gov_recalls_changes clearly.

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 explicit when and how: pass since=<next_cursor>, omit once to bootstrap, and recommends polling the free sibling gov_recalls_changes and paying only when there's something to fetch. That's a concrete routing rule to an alternative.

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