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

With no annotations, the description carries the full burden; it does disclose the return artifacts (video recording, pass/fail verdict against written criteria, measurements), which is genuinely useful since no output schema exists. It says nothing about prerequisites (site access, codes, whether a human or robot executes), what happens when the action fails or the deadline passes, or how budget_cap constrains the run — significant gaps for a real-world physical operation.

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?

Two sentences: the verb front-loaded, examples inline, then the outputs. No filler; the example list is a bit dense but each clause adds distinguishing detail.

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?

A consequential real-world action tool with zero annotations, no output schema, and 0% parameter coverage needs far more: execution model, failure/timeout behavior, cost implications of budget_cap, and deadline semantics are all absent. The return-value sentence is the only thing preventing a 1.

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 5 parameters, so the description must compensate. It only hints at two of them — 'action' via examples and 'pass_criteria' as 'written criteria' — while 'address', 'deadline', and 'budget_cap' are never mentioned, leaving format and semantics (is address a street address, a unit, a coordinate?) undefined.

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 specific verb ('perform a defined physical action') plus the reporting outcome (video, pass/fail against written criteria, measurements), and the examples (open door with code, test lock, run appliance, stand-and-measure) make the resource concrete. It never names or contrasts with a sibling, and 'stand where the robot will stand and measure' overlaps noticeably with stand_in, so an agent cannot fully rule out the alternatives from this text alone.

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?

No explicit when-to-use or when-not-to-use statement and no mention of the sibling tools (stand_in, verify_location, environment_assessment, witness_event) that overlap in domain. Usage is only inferable from the example actions and the presence of pass_criteria.

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