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

Annotations already declare read-only, idempotent, closed-world, and non-destructive behavior, so the safety profile is covered. The description adds a genuinely useful behavioral fact beyond that: a county absent from the file returns an error, which tells the agent to expect failure rather than an empty result. It does not describe the return format (number vs record), which keeps it from a 5.

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 with the resource and its backing file front-loaded, and the error condition placed where it is needed. The middle sentence restates the stored-figure idea, which is slightly redundant but does serve the sibling-distinction purpose.

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 two-parameter read-only lookup with no output schema, the description covers what is retrieved, where it comes from, and the one failure mode. It omits the state-parameter format and whether a state missing from the file also errors, so it is not fully closed but is adequate for its complexity.

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%: county carries a schema description (name/slug/FIPS, omit for state summary) while state is undocumented. The description adds only that a value is retrievable 'for a state or county', which does not compensate for the undocumented state parameter format. Baseline 3 fits a lookup where the schema does part of the work.

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 ('gross rent yield stored for a state or county') and names the concrete backing store (gross-yield.json). Crucially, it distinguishes itself from the sibling calculate_gross_yield by emphasizing 'The yield is the file's stored figure' rather than a computed one.

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?

'The yield is the file's stored figure' implies this is a static lookup versus a computed tool, which is a usable signal, but the description never explicitly says when to choose this over calculate_gross_yield or what prerequisites apply. No exclusions, no named alternatives — usage is left to inference.

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