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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds behavioral context beyond the annotations by specifying that the tool returns scope choices, missing inputs, and questions, and that it requires no account or saved project. This is useful supplementary context.

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 two sentences, concise and front-loaded with the primary action ('Start a conversation...'). It avoids unnecessary detail and is easy to scan.

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?

Given the tool's complexity (3 top-level parameters, a large nested scope object with over 80 fields, and an output schema), the description is far too brief. It does not explain the shape of the return value, how to map user inputs into the nested object, or what 'supported scope choices' means in practice. This leaves significant gaps for an agent trying to use the tool correctly.

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 effectively zero (only approximateSize has a brief description). The tool description does not compensate by explaining the parameters (jobType, postcodeArea, scope) or how to populate the nested scope object. Parameter names and enum values give some clues, but the description adds no semantic guidance for a complex input structure.

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 the tool's purpose: starting a conversation to gather estimate requirements and returning supported scope choices, missing inputs, and questions. It does not explicitly name sibling tools (calculate_guide_price, compare_guide_scenarios) to differentiate, but the focus on gathering inputs rather than calculating or comparing makes the intended use evident.

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 description implies usage for initial requirements clarification ('Start a conversation about... budget') but does not explicitly state when to use this tool versus the sibling tools (calculate_guide_price, compare_guide_scenarios) or provide conditions for when it is not appropriate. No alternative guidance is given.

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