start_thread

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

Beyond the annotations, it discloses concrete side effects: changing files, incurring provider charges, default approval requirement, lack of worktree support, and retry semantics for operationId. This goes well beyond the readOnly/destructive flags. No contradiction with 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?

Five short sentences each add distinct information, with the core purpose first. No filler or redundant restatement of 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?

The description covers side effects, defaults, limitations, and retry behavior, but with 8 parameters, low schema coverage, and no output schema, an agent still lacks guidance on return values, model selection, interaction mode, and how the IDs relate. It is adequate but has clear gaps.

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 only 13% (only operationId is documented), and the description compensates minimally. It implies the instructions parameter and notes the approval-required runtimeMode default, but it doesn't explain environmentId, projectId, title, modelSelection, or interactionMode. With low schema coverage, the description should carry more of this burden.

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 opens with the specific verb-resource pair, 'Create a thread and send instructions to its agent,' and situates it in the existing project workspace. This clearly differentiates it from sibling tools that list environments/projects or send messages to an existing thread, even though those siblings aren't named.

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?

It provides clear context: the thread is created in the existing project workspace, defaults to approval-required, and cannot create worktrees. It also gives retry guidance. However, it does not explicitly identify which sibling to use instead, so it stops short of the 5 level.

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