aeo_audit_prompts

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

Annotations declare readOnlyHint=true, which is consistent with the description. The description adds value by detailing what the audit produces (intent, metric, play, recommendation) and the expected input structure. It does not contradict annotations and provides useful behavioral context beyond the read-only hint.

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: a concise summary followed by the parameter format. Both sentences are informative and necessary, with no fluff or repetition of schema information. It is front-loaded with the primary purpose.

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 no output schema, the description adequately explains the nature of outputs (per-prompt intent, metric, play, recommendation). It also covers the key input structure. However, it leaves some jargon undefined (e.g., 'play', 'realistic metric') and does not clarify the exact return format, which might be ambiguous for a general agent. Still, for a specialized AEO tool, it is fairly complete.

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 0%, so the description must compensate. It does for the required 'prompts' parameter by specifying the structure: [{id, text, intent?, mention_rate?, citation_rate?}]. However, it does not explain 'config' or 'use_llm', though these are optional and their names are somewhat self-explanatory. The main required parameter is well covered.

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: 'Audit a tracked-prompt set' with specific outputs (per-prompt intent, metric, play, keep/cut/rewrite recommendation). This distinguishes it from siblings like aeo_generate_prompts (generate) and aeo_filter_prompts (filter), which have different purposes.

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 auditing existing tracked prompts but does not explicitly state when to use it versus alternatives like aeo_generate_prompts or aeo_filter_prompts. There are no when-not-to-use guidelines or alternative names mentioned, leaving the context to be inferred.

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