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

Beyond the annotations (read-only, idempotent, non-destructive), the description discloses that missing details return 'needs_input' and that the tool returns a 'rich budget card with VAT, assumptions and exclusions'. It also states it uses only conversation-supplied data, providing extra behavioral context without contradicting annotations.

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?

The description is concise and front-loaded with usage conditions. It covers purpose, supported work, constraints, output, and exclusions in five sentences without unnecessary detail, making it easy to parse and act on.

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?

The description includes explicit exclusions that help route away from non-applicable requests, and it summarizes the output format and error behavior. However, it does not explicitly reference sibling tools like 'compare_guide_scenarios' or 'get_estimate_requirements', so some differentiation relies on inference. The output schema is indicated but not shown, so the description's summary is sufficient but not exhaustive.

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?

The description mentions 'scope, area in square metres and outward postcode', giving a partial hint about inputs, but it does not explicitly explain the 'jobType' top-level enum parameter. The nested scope object contains many fields with limited descriptions, so the parameter semantics are not fully addressed. The note about 'needs_input' mitigates some ambiguity, but the description could be more precise about which parameters are required for different job types.

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?

The description clearly states when to use the tool ('when a user asks how much UK building work could cost...'), what it calculates ('an indicative GBP range'), and lists supported work types. It also explicitly distinguishes from excluded use cases ('Not for property valuations, mortgages, non-UK work...'), making the purpose unambiguous.

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?

Provides explicit when-to-use ('Use this when...') and when-not-to-use ('Not for...') guidance. It also instructs the agent to ask the user rather than guessing when details are missing, which is a clear behavioral directive for usage.

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