template_pick

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

Without annotations, the description discloses key behaviors: it does not access stored templates, requires explicit caller-supplied candidates, is synchronous, and returns an ordered array of template IDs. This goes beyond the schema and gives the agent confidence about side effects and invocation flow.

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?

Five tight sentences, each providing distinct information: what it does, a critical caveat, synchronous behavior, input source, and return format. No redundant or vague wording.

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 no output schema and no annotations, the description covers purpose, input source, return shape, and behavior. It even prevents a common mistake by warning against assuming server-side template reading. This is comprehensive.

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 covers 100% of parameters with descriptions, so baseline is 3. The description adds valuable guidance that the templates parameter should be the full-detail output from template_list, with the return format clarified as ordered IDs. This raises it to 4.

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: an AI re-ranker that scores and picks the N best-fitting templates from a caller-supplied list. It explicitly distinguishes itself from tools that read stored templates by noting the caller must supply candidates, differentiating from sibling template_list.

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 explicit when-to-use guidance: call template_list first, then pass the full-detail templates array to this tool. It also states what the tool does NOT do (does not read stored templates server-side) and that it is synchronous/no polling needed, giving clear context versus alternatives.

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