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

Annotations indicate a non-destructive write operation (readOnly=false, destructive=false, idempotent=false). The description adds valuable behavioral context: cost ('Free'), specific return structure ('version object with id'), parsing behavior, and workflow integration. Does not cover error states or rate limits, preventing a 5.

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?

Four dense sentences with zero waste. Front-loaded with the core action (Upload), followed by processing, return value explanation, workflow context, and cost. Information hierarchy places the most critical operational details first.

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?

Compensates effectively for the missing output schema by detailing the return object structure ('version object with id') and its role in the workflow. Covers file formats, processing behavior, and downstream dependencies. Minor gap regarding error handling or file size constraints prevents a 5.

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 100%, with both 'file' and 'filename' fully documented (base64 encoding, content-type detection). The description mentions supported formats (PDF/DOCX) which aligns with schema but does not add significant semantic depth beyond the structured schema definitions. Baseline 3 is appropriate given schema completeness.

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?

Explicitly states the core action ('Upload a CV file'), processing steps ('Parses the document, creates a CV version'), and deliverables ('returns structured sections with word count'). Distinctly positions itself as the entry point ('first step in the CeeVee workflow') and differentiates from sibling tools by specifying exactly which tools consume its output (ceevee_analyze_positioning, etc.).

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 clear sequencing guidance by stating it is 'the first step in the CeeVee workflow' and explicitly mapping the return value's usage across five downstream tools. Lacks explicit negative guidance (e.g., 'do not use if you already have a cv_version_id') but strongly implies this is the creation path vs. retrieval alternatives like ceevee_get_version.

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