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

All annotations are false, so the description carries the full burden and meets it: it discloses the parse pipeline, that save=true persists the profile and rebuilds the job feed (a real side effect), that save=false returns the parsed profile for review only, and the 8 MB input cap. No contradiction with annotations — the described write behavior aligns with readOnlyHint=false, and the side-effect disclosure fits idempotentHint=false.

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 sentences with zero filler: trigger condition is front-loaded, followed by the parse pipeline, the save-toggle semantics, and the size limit, each clause earning its place. It avoids restating schema content like base64 encoding or parameter names.

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?

With no output schema and no annotation support, the description explains exactly what the agent gets in each mode — a saved profile with a rebuilt feed, or a review-only parsed profile whose contained fields are enumerated. Input constraints (format, size) are covered; the only minor omissions are error behavior for oversized/unsupported files and whether an existing profile is overwritten, which are secondary for a 3-parameter upload tool.

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?

The schema documents filename and content_base64 but leaves save completely undescribed; the tool description compensates by fully explaining both save modes and their downstream consequences (feed built vs. review only). It also adds accepted formats (PDF/DOCX from the title) and the 8 MB constraint, which are not in the schema, pushing it above the baseline for its 67% schema coverage.

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?

States a specific verb + resource ('Upload a CV file and turn it into the account's profile') and names the exact parsed fields (name, contact, summary, roles, skills, languages, education), so an agent knows the transformation this performs. The opening trigger phrase ('Use when the person shares or mentions their resume/CV') plus the explicit profile-building behavior distinguishes it from siblings like update_profile and preview_tailored_cv without needing to open their schemas.

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?

Opens with an explicit trigger condition and illustrative user quotes ('here's my resume', 'use my CV'), which is strong guidance for when to select this tool. It also tells the agent the save=true vs save=false trade-off (persist and build feed vs. review only), effectively a when-to-persist guideline. It does not explicitly name alternatives or exclusions (e.g., 'use update_profile for direct field edits'), which keeps it from a 5.

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