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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description correctly spends its words elsewhere: it discloses the data source, that results are report counts rather than confirmed incidents, that no narratives are returned, and that each call costs 1 credit. That is real behavioral context beyond the structured fields, though it says nothing about result shape or limits per outcome bucket.

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 action and breakdown before the audience and caveats, and every sentence carries substance. The caveat material is slightly repetitive in spirit (reports-not-incidents is restated across the outcome note and the caveat sentence), but it is defensible for a tool whose output is easily misread.

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 one-parameter, no-output-schema tool this is close to sufficient — it tells an agent what categories come back and that no narratives are included, compensating for the absent output schema. The remaining gap is scope of matching (does a brand name like "Omnipod" aggregate across models?), which matters for interpreting the counts.

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% and the single parameter already documents itself with examples ("insulin pump", "Omnipod"). The description's parenthetical "generic type or brand name" essentially restates the schema, adding no syntax, normalization, or matching-behavior guidance. Baseline 3 applies when the schema carries the load.

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 (counts) and resource (reports in FDA MAUDE) scoped by device and broken down by reported outcome category. It also carves out a negative boundary (no individual report narratives), which keeps it distinct from narrative-level siblings. It stops short of naming which sibling to pick instead of fda_device_recalls or fda_device_510k_clearances, so it isn't fully differentiated.

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 journalists, litigation researchers and patients a quick sense of the reporting record" supplies explicit use context, and "cannot be used to rank how safe devices are" states a when-not-to-use constraint. What's missing is routing language: no alternative tool is named for callers who actually want recall records, clearance history, or individual reports.

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