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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is fully covered elsewhere. The description adds modest behavioural detail ('Returns result and reciprocal', degrees/radians handling) but does not expand on domain limits for inverse functions. With annotations carrying the heavy load, this is adequate.

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?

Three short sentences, front-loaded with the capability and then usage, inputs and cross-reference; nothing is padded. The input-enumeration sentence is close to redundant given a fully documented schema, which keeps it just under a 5.

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 pure, idempotent calculator with an output schema and full annotation coverage, the description supplies what an agent needs: capability, unit modes, intended domains and a bundle pointer. Only the absence of any sibling-routing note keeps it from being fully complete.

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% with two enums, so the schema already documents func, unit and value completely; baseline is 3. The description only restates the parameter list ('Inputs: function, value, unit') and adds no semantics such as whether value is interpreted in degrees before the unit applies, or valid domain ranges for asin/acos.

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 ('Compute') plus the exact resource — the six trig functions — and the unit modes, which is far more precise than the tautological 'Calculate Trigonometry' title. It stops short of explicitly distinguishing itself from near-neighbours like calculate_angle_convert or convert_angle, so it is clear but not fully sibling-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?

'Use for geometry, physics, navigation' gives domain context, and 'See list_bundles for related math calculators' points to a discovery path. However there is no when-not guidance, no exclusion of the angle-conversion siblings, and no prerequisite information, so usage is only implied rather than stated.

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