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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety burden is lifted. The description adds two genuinely non-obvious traits beyond that: results come back as compact records with pagination, and an empty query returns the full list rather than an error — important given zero required parameters.

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, front-loaded clauses with no filler: what is searched, the optional filter, the return shape, and the empty-query edge case. Nothing repeats the annotations or the schema.

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 simple four-parameter read tool with an output schema, the description covers the essentials: scope of search, filter semantics, result shape, pagination, and the zero-parameter default. Only the relationship to sibling tools is left unstated.

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 50%: query and family are documented, while limit and offset rely on their numeric constraints only. The description compensates meaningfully for query by naming the searchable fields (common name, scientific name, guide text) and reinforces that family matching is exact, adding semantics the schema text does not carry.

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 (search) plus the exact fields searched (common/scientific names and guide text) and the optional family filter, so the agent knows precisely what the tool retrieves. It does not, however, explicitly contrast itself with get_bird (single-record fetch) or list_families, leaving the sibling differentiation to inference.

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?

Usage is implied rather than prescribed: 'optionally filter by exact family' and 'Empty query lists all birds' hint at how to drive the tool, but there are no explicit when-to-use/when-not rules and no named alternative for retrieving a single bird or for enumerating families. An agent can proceed, but must infer the routing.

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