Mechanics for ONE section, by its role

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

With no annotations, the description carries the full burden of behavioral disclosure. It transparently explains the internal logic: 'filtered first by the catalog facets that actually correspond to the role, then ranked by the free-text need.' It also discloses a key behavioral trait: the ability to return 'NOTHING' for a role rather than returning a false positive. This goes beyond a simple 'returns suggestions' and is genuinely informative, though it doesn't cover every edge case or output detail.

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 slightly verbose but each sentence adds value. It front-loads the core function, then provides a crucial differentiator ('Crucially, it can answer that the catalog has NOTHING'), and ends with actionable guidance for the 'none' verdict. The examples (counters, pricing tables, etc.) are helpful but could be trimmed without losing meaning.

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 (6 parameters, no output schema) and its role in the planning workflow, the description covers the essential context: purpose, usage context, and alternative behavior. It mentions the 'adopted' parameter indirectly through the contrast with get_integration_contract, and it explains what to do on 'none.' It doesn't detail the return schema, but that is fine since no output schema exists. Overall, it's a well-rounded description.

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 input schema already provides detailed descriptions for all 6 parameters, covering 100% of them. The description adds a little by connecting 'section role' and 'what that section has to do' to the role and need parameters, but it doesn't elaborate on the other parameters, and the schema already does that heavy lifting. A score of 3 is the baseline for high schema coverage, and the description adds marginal value above it.

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 function: 'Given a section role from plan_page and what that section has to do, returns ranked candidate components.' It uses a specific verb ('returns'), names the resource ('candidate components'), and explains the filtering and ranking process. It also distinguishes itself from search_components by highlighting its ability to return a 'none' verdict, which is a unique capability.

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 gives explicit usage guidance: 'Prefer this over search_components when building a planned page.' It also explains when search_components is insufficient and provides an alternative action for when the verdict is 'none': 'write the section from the motion system tokens.' This clearly outlines when to use the tool and what to do in a specific outcome.

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