write_changelog_draft

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

With no annotations provided, the description carries the full behavioral burden and largely delivers: it discloses that reads happen via git log, that remotes are never accessed, and that git history is never rewritten. The dryRun preview behavior is also surfaced. It does not explicitly flag that the non-dryRun path mutates the filesystem by writing outputPath, though 'Write a CHANGELOG.md' makes this fairly inferable.

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 with zero waste: purpose first, then the preview flag, then the safety constraints. Every sentence earns its place and the structural boundary (local working tree only) is front-loaded.

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 an 8-parameter tool with no annotations and no output schema, this description covers the core behavior, safety profile, and operation domain well. The main gap is return-value disclosure: with no output schema, an agent doesn't know what a successful call returns (e.g., written path, diff, success message), since only the dryRun preview outcome is hinted at.

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 is 3. The description adds modest value by framing to/from as local git refs and highlighting dryRun as the preview mechanism, but most parameter meaning already lives in the schema. It does not add formats, edge cases, or interaction details beyond what the schema states.

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 — 'Write a CHANGELOG.md draft for a version from local git history' — which clearly differentiates it from siblings: generate_release_notes (likely remote/API-based) and group_conventional_commits (an analysis/grouping operation). The local-only scoping reinforces the distinct identity.

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?

Implied usage is present through constraints ('Operates on a local git working tree only', 'Does not access remotes or rewrite history'), which tells an agent when this tool is appropriate over a remote-capable alternative. However, it never names the siblings or gives explicit when-to-use/when-not-to-use guidance, leaving differentiation to inference.

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