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

Annotations already declare the readOnly/idempotent/destructive safety profile, so the description correctly adds other behavioral facts: results are real-time, capped ('Can match many sites, so results are capped'), and each result carries the site's latest reading. 'Keyless' adds an auth-relevant disclosure no structured field conveys.

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 sentences, no wasted words. Core purpose is front-loaded, followed by return-shape/usefulness, then a behavioral warning and an auth note. Every sentence earns its place.

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 3-param discovery tool it is nearly complete: safety annotations, full parameter schema, purpose, and a return-form hint are all present. The only shortfall is no detailed result structure (no output schema), leaving the identifying fields of each returned site unspecified.

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 covers 100% of parameters with descriptive text (state, parameter_code with default '00060', limit with default 30/max 60), so the baseline is 3. The description reinforces these concepts ('US state', 'given parameter', 'results are capped') but adds no new syntactic or formatting detail beyond the schema.

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-resource pair ('Discover active USGS gauge sites') with clear scope ('in a US state... currently reporting a given parameter'). The real-time qualification and 'useful for finding which gauges are live' clearly position it against data-retrieval siblings like current_conditions and daily_values.

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?

'useful for finding which gauges are live in a region' gives an agent a concrete task context for when to invoke this tool. However, it names no explicit alternatives or when-not-to-use conditions to route around siblings, so it stops short of a 5.

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