get_fix_recipe

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

States 'Non-destructive' which is a key behavioral trait. However, with no annotations, it doesn't disclose authentication, rate limits, or what happens if there's no current rejection. Minimal but present.

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?

Two concise sentences, front-loaded with purposecars. No 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 simple tool with one param and no output schema, the description is adequate but could clarify what 'current rejection' refers to and whether any prerequisites exist. It lacks explanation of the recipe structure, but that may be acceptable.

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 coverage is 100% and the description doesn't add any parameter meaning beyond what the schema already provides. Baseline 3.

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 returns 'code-free Appo remediation recipes for the current rejection', specifying the verb (returns), resource (recipes), and scope (current rejection). This distinguishes it from siblings like get_rejection and diagnose_issue.

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 phrase 'for the current rejection' implies usage context, but there's no explicit guidance about when to choose this over get_rejection or diagnose_issue. Alternatives aren't mentioned, but the context is somewhat implied.

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