analyze_document

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

Strong supplemental context: while annotations confirm read-only/idempotent safety, the description details the specific JSON structure returned (listing 13+ distinct metrics like heading counts, code block counts, reading time). This compensates for the missing output schema.

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?

Optimal structure: Two sentences, front-loaded with action ('Analyze...'), followed by output specification. Zero redundancy—every word earns its place.

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?

Complete for the tool's complexity: despite lacking an output schema, the description enumerates return values in detail. With rich annotations (4 boolean hints) and 100% parameter coverage, this adequately equips the agent.

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% ('markdown' parameter fully described), so the description does not need to add parameter semantics. Baseline 3 is appropriate as the schema carries the semantic burden.

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?

Excellent specificity: 'Analyze' (verb) + 'Markdown document' (resource) + 'return comprehensive statistics' (output). Clearly distinguishes from conversion siblings (convert_to_*) and extraction siblings (extract_*) by focusing on statistical analysis rather than format transformation or content isolation.

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?

Implied usage is clear (analysis vs conversion), but lacks explicit guidance on when to choose this over extraction tools like extract_code_blocks or extract_links, or generator tools like generate_toc which overlap conceptually with document analysis.

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