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

Annotations already declare destructive/not-idempotent/not-read-only, yet the description adds substantial non-annotated behavior: un-named entries stay untouched in ops mode, entries missing from payload are removed, omitted keys retain stored values while ""/[]/null clears, experience date validation rules, and the not_found/invalid_payload error contract. This is the concurrency, data-loss, and validation context an agent needs for a destructive mutation.

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?

Front-loads purpose, then the mode-exclusivity rule, then semantics, then errors — a logical structure with no filler sentences. It is on the long side because it re-lists every section shape that the schema already contains, which is redundant rather than wasteful, so only a small deduction applies.

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?

Covers everything needed for a destructive, versioned edit tool: mode exclusivity, id provenance, concurrency guard, per-field merge vs clear semantics, validation rules, and error strings. An output schema exists, so the brief return note ('edited section with entry ids and the new content_version') is appropriate rather than required.

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 top-level schema is an opaque single 'input' wrapper (0% description coverage reported), so the description carries the burden of explaining ops vs payload semantics, expected_content_version, and id-based matching — and it does so thoroughly. It loses a point because the long section-shape enumeration largely duplicates what the nested payload schema already documents rather than adding new semantics.

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?

Opens with a specific verb+resource ('Apply an edit to one section of a resume') and enumerates the twelve editable sections, so an agent immediately knows the scope. It also implicitly separates itself from get_resume ('get_resume reads the whole resume') and from list_resumes/rename_resume siblings, which is exactly what a sibling-differentiating definition should do.

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?

Explicitly states the two modes and the selection rule ('Two modes, exactly one per call'), explains when each applies (targeted ops vs whole-section payload), and covers prerequisites including where entry ids come from (get_resume) and what happens on conflict (expected_content_version → 'resume_changed'). Alternatives for reading content are named rather than left to inference.

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