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

The description adds substantial behavioral context beyond annotations: mode-specific return types, anonymous vs authenticated execution, and specific auth setup for stdio and HTTP. The word 'Create' might suggest mutation, but readOnlyHint, idempotentHint, and the overall context make clear this is a compute/read operation. No contradiction with 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?

Four sentences with a front-loaded core action, followed by conditional usage and auth context. Every sentence is informative and there is no redundancy or fluff.

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 tool with 10 optional parameters, two modes, and auth requirements, the description covers the primary behaviors, return values, and auth setup. It does not cover edge cases like conflicting parameters, but the schema fills in parameter-level details adequately.

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?

All 10 parameters have schema descriptions, so baseline is 3. The description adds value by grouping parameters into modes (task constraints vs listing identifiers) and clarifying that slug is a listing alternative, which helps the agent understand which parameters to use together.

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 it creates a router-aware quote and explicitly distinguishes two modes based on parameters: task+constraints returns ranked providers, while capability_id/listing_id/slug returns a listing-specific price, trust snapshot, and next-step guidance. This specificity distinguishes it from sibling tools like quote_service and browse_services.

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?

It provides clear conditional usage: pass task+constraints for task mode, or capability_id/listing_id/slug for listing mode. It also explains auth requirements per mode (anonymous for listing, API key for task). However, it does not explicitly state what to do when multiple mode identifiers (e.g., task and capability_id) are passed together, nor name alternative tools.

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