Edit or manage a project file

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is partly covered; the description still adds material non-annotated behavior: preview-by-default semantics, the mandatory expectedSha256 concurrency guard for existing files, recoverable backups on writes/moves/deletes, and the binary-write refusal. Nothing here contradicts the annotations.

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 sentences, front-loaded with the operation set, then the default behavior, then the constraints and sibling routing. No filler and no repetition of the title or schema field text.

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 10-parameter mutation tool with no output schema, the description covers the important preconditions (SHA check, backup, preview) and the escape hatches (scf_edit, desktop tools). The gap is the return surface: with no output schema, the shape of a preview versus an applied result is left implicit, which is the one thing an agent cannot infer elsewhere.

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%, so the baseline is 3, but the description adds cross-parameter semantics the schema cannot: preview behavior is governed by confirm (default off), expectedSha256 is mandatory only for existing source files, and backups apply per operation type. It does not, however, add distinctions between write vs patch payloads beyond the schema's own field docs.

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?

The first sentence names the specific resource (one file) and enumerates the five concrete operations (write, exact-patch, copy, move, delete), so an agent can distinguish it from project_create, project_clone, or project_restore_file. It also explicitly separates itself from scf_edit and the desktop/GDF tools, which is exactly the differentiation a sibling-heavy tool needs.

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 affirmative conditions (preview by default; existing files need expectedSha256) and negative routing rules: general binary writes are refused, SCF scalar inputs belong in scf_edit, GDF drawing changes belong in desktop tools. This is explicit when-to-use / when-not-to-use / alternative guidance rather than implied context.

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