bisect_start

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

With no annotations, the description carries the full behavioral burden and largely fails: it does not say whether the session persists across calls, what state it creates, how it interacts with bisect_good/bisect_bad/bisect_end, or what auth/tier is actually required. The only behavioral hint ('Requires Kiln Pro') is stated as part of an upgrade pitch rather than as a clear access constraint for this tool.

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?

The first sentence is well front-loaded, but the remaining two sentences are paywall/marketing content ('unlimited textures and decorations', an upgrade URL) that consumes the bulk of the description without helping the agent invoke the tool. Roughly two-thirds of the text does not earn its place.

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 mutation tool with no annotations, no output schema and 0% parameter coverage, the description should at minimum explain the bisect workflow (start → bisect_good/bisect_bad → bisect_end) and define its inputs. It omits all of that and substitutes promotional copy, leaving the agent unable to call the tool correctly.

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 0% across six parameters (operator, artifact_id, artifact_type, target_check, good_version_id, bad_version_id), and the description explains none of them — not even the format of version IDs or what a 'target_check' or 'operator' value looks like. Nothing compensates for the schema gap.

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 opening sentence gives a specific verb and resource — 'Start a new bisect session — find where something broke' — which an agent can distinguish from list_bisect_sessions, bisect_end, bisect_good and bisect_bad. However, it never names or contrasts those siblings, and the remainder of the text is unrelated marketing copy that dilutes the signal.

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?

There is no guidance on when to start a bisect versus resuming one or recording a result with bisect_good/bisect_bad, nor on prerequisites such as needing good_version_id and bad_version_id up front. The only quasi-usage statement is 'Requires Kiln Pro', which is buried in an upsell block and is ambiguous about whether it applies to this tool or to the advertised features.

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