open_lab

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

Even though no annotations are provided to set a baseline, the description goes well beyond minimal expectations for behavioral disclosure. It explicitly states the tool is read-only ('Read-only'), clarifies there is no side-effect or session mechanism ('every change [...] is its own direct call, no prior "open" needed'), describes search behavior (recursive, case-insensitive substring match), and specifies the output includes lock status and suggested next steps. This level of detail is exemplary for a tool lacking 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?

The description is efficiently structured with short sentences and a logical flow: purpose first, then behavioral caveats, then search behavior, then parameter details. Every sentence adds value. It could be improved by moving the parameter docs to a more standardized format or removing redundancy in the sibling-tool reference, but overall it's well-proportioned.

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?

Given the tool's moderate complexity (3 parameters, but no required ones) and the presence of an output schema (meaning the description doesn't need to explain return format), the description is remarkably complete. It covers purpose, behavioral constraints, search semantics, disambiguation mechanics, and parameter semantics—all within a compact space. No critical gaps remain for an agent to use this 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?

Despite a 0% schema description coverage (the schema provides no human-readable parameter descriptions), the description's parameter documentation (Args section) adds substantial meaning beyond the bare schema. It clarifies `name` is 'Required' (despite the schema not marking it required, the description states it's required behaviorally), `search_path` defaults to '/', and `selection` is only needed when multiple labs match. The description explains the behavioral semantics of each parameter, though it could further specify the format for `name` and `selection` (e.g., what 'full name/path' looks like).

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 immediately states the tool's core purpose: 'Look up a lab by path or name substring, report its lock status, and suggest next steps.' It clearly distinguishes itself from siblings like `delete_lab`, `create_lab`, and `get_lab` by emphasizing that this is a read-only lookup operation that reports lock status and suggests next steps, not a mutation or a simple fetch. It also explicitly differentiates from any 'open for editing' session concept.

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 tells the agent when to use this tool ('Look up a lab...report its lock status, and suggest next steps.') and when not to ('Read-only -- there is no "open for editing" session'). It also provides clear guidance on usage patterns: how search works ('recursively under `search_path`; matching is case-insensitive substring'), what happens with multiple matches ('they're listed and you pick one'), and how disambiguation works ('via `selection`'). It even name-drops a sibling (`delete_lab`) to clarify search behavior.

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