file_edit

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

With no annotations, the description carries the full burden and does well: it discloses the reference-frame rule (line numbers are against the ORIGINAL file), a hard constraint (line ranges must not overlap), failure semantics (replace_text fails unless it matches expect_count, default 1), and a safe preview path via dry_run. Missing are permission/backup behavior and what the dry_run output actually looks like, so not 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?

Three dense sentences, each front-loaded with high-value constraints: batching first, then op list, then the line-number/overlap rule, then failure and preview semantics. No filler and no repetition of the schema.

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?

For a multi-op mutation tool with no output schema and no annotations, the description covers the operation model, ordering constraints, failure conditions, and preview path — enough to call it correctly. It leaves the return value of a write/dry_run unexplained and does not address concurrent-edit or stale-file handling beyond expect_match's mention in the 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?

Schema coverage is 100%, so the baseline would be 3, but the description adds genuine meaning beyond the schema: the non-overlap constraint and original-file line numbering for start_line/end_line, expect_count's default of 1 and all=true override for replace_text, and dry_run's diff-preview behavior. It doesn't explain eol or expect_match/allow_no_match, which the schema covers.

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 and resource with scope ('Patch parts of a file — several edits in ONE call') and enumerates the op types, which makes it unmistakably the incremental-edit tool rather than file_write. It does not explicitly name a sibling or draw the boundary against file_write, so it stops short of a 5.

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?

Gives real usage context: plan all edits from a single file_read because line numbers refer to the original file, and preview with dry_run=true. It also distinguishes replace_text (with expect_count/all) from the line-based ops. There is no explicit 'when not to use' or named alternative (e.g. use file_write for a full rewrite), so it is clear but not exhaustive.

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