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

With no annotations provided, the description carries the transparency burden. It reveals the tool is format-agnostic and never prescribes frameworks or architecture, and explains the nuance of each guidance level. However, it does not explicitly state the output format (though text is implied) or clarify the discrepancy between schema default null and stated default 'full'.

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 a single paragraph that is moderately long but every sentence adds useful context. It front-loads the core function, then explains the guidance levels, provides an alternative, and ends with the entity list. It could be trimmed slightly as some guidance-level detail duplicates schema descriptions, but it remains efficient and logically organized.

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?

The description explains the tool's purpose, guidance levels, entity availability, and constraints (format-agnostic), which is substantial for a guidance tool with no output schema. However, it does not describe the structure or length of the returned guidance, and the lack of annotations means no safety/read-only hints are provided, leaving some gaps for a tool with no output schema.

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?

Although schema coverage is 100%, the description adds significant value by listing all available entities, which the schema only samples. It also elaborates on the meaning of guidance values beyond the concise schema descriptions, including 'softened vocabulary' and 'strong visual-design instincts', helping the agent choose appropriate parameter values.

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 AdCritter design guidance for a given entity, with specific content areas (screen experiences, API integration patterns, design philosophy). It also distinguishes itself from siblings by recommending alternative tools for API integration bindings, making it highly differentiated.

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?

Provides explicit when-to-use guidance for each guidance level: 'full' for step-by-step prescription, 'patterns' for balanced hints, and 'facts' for callers with strong design instincts. It also explicitly names adcritter_get_api_reference and adcritter_get_usage_guide as alternatives for API bindings, giving the agent clear decision criteria.

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