Semantic Bisect

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

Goes well beyond the annotations: it discloses that execution happens in a temporary git worktree and that 'the user's checkout is untouched,' which explains why destructiveHint=false holds despite running an arbitrary shell command. It also warns that the user's own shell command is executed and must be confirmed, covering the openWorldHint risk profile with concrete context.

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 outcome and followed by mechanism and the safety caveat. Every sentence earns its place and nothing is repeated from 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 six-parameter tool with no output schema, the description conveys the essential model: what it searches for, how it evaluates each commit, and the sandboxing. It omits practical detail an agent might want, such as what the result reports and that the run may be long because the command executes per commit.

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 schema already documents repo, good, bad, command, symptom, and timeoutSec, making 3 the baseline. The description reinforces the semantics of good/bad/command/symptom in prose but adds no syntax, format, or default detail beyond what the schema provides.

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 precise verb and outcome: 'Find the commit that introduced a problem a normal test can't detect,' which immediately distinguishes it from ordinary git bisect. It goes on to name the mechanism (git worktree, the `command`, the `good`/`bad` range) so an agent knows exactly what the tool produces. No sibling in the provided list overlaps, so no differentiation is needed.

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 qualifier 'a normal test can't detect' tells the agent when this tool is warranted versus a deterministic bisect, and the closing sentence gives an actionable prerequisite (confirm the shell command with the user first). It stops short of stating an explicit when-not or naming an alternative tool, so it is clear context rather than full routing guidance.

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