topos_assess_worktree_change

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds meaningful behavior: the baseline is read from git via git show with default HEAD, compared to the working-tree file, and the tool is stateless with no prior call needed.

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 concise sentences, front-loaded with the core function and immediately followed by the alternative path. Every sentence earns its place, with no filler or tautological restatement.

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 6-parameter tool with no output schema, the description provides essential selection context: what the tool does, how the baseline is sourced, and when to delegate to snapshot-based flows. It doesn't describe the output shape, but the assess verb and sibling context make the purpose and typical usage sufficiently clear.

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 83%, so most parameters are already documented. The description adds context to baseline_ref by specifying the git show mechanism and default HEAD, and clarifies that filepath refers to the current working-tree file. This goes beyond the schema's brief field labels.

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 description states a specific verb+resource: 'Assess an in-place edit against a git revision', and names it 'the common refactor loop'. It clearly distinguishes from sibling assess tools by emphasizing the git baseline vs working-tree comparison and explicitly directs untracked/new files to begin_refactor + assess_snapshot.

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?

The description explicitly says when to use the tool ('the common refactor loop') and provides an explicit alternative for untracked/new files or uncommitted pre-edit baselines. It also notes that no prior call is required, which helps with session sequencing.

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