sandbox_collect_evidence

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the notable behavioral detail that the observation record is 'host-only,' implying where evidence is persisted, but it says nothing about where artifacts are written, naming, or whether repeated calls overwrite prior evidence. 'Save' is slightly at odds with readOnlyHint, but saving a new evidence artifact is a common convention for read-only capture tools, so this is context rather than a true contradiction.

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?

A single compact sentence with the verb front-loaded and no filler. The item list is dense but each element carries information about scope; a short clause on output location would have been the only addition worth its length.

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?

With zero parameters and no output schema, the description is the agent's only source of information, and it covers what is collected but not where evidence lands or how it is retrieved afterward (presumably via sandbox_artifact). Adequate for a no-arg capture call, but the retrieval link is left implicit.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The enumerated evidence types are the only variable part of the call, and they are adequately conveyed.

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 ('Save') and enumerates the evidence types it captures (screenshot, window list, UI inspection, hashes, host-only observation record), so the agent knows exactly what this tool produces. It does not, however, distinguish itself from overlapping siblings like sandbox_screenshot, sandbox_windows, and sandbox_inspect, leaving the agent to infer that this is the bundled/aggregate variant.

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 statement of when to use this composite collector versus the individual siblings (sandbox_screenshot, sandbox_windows, sandbox_inspect), nor any prerequisite or ordering guidance. The only implied usage is 'capture everything at once,' which the agent must infer from the enumerated item list.

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