snapshot_storage

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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint=false), it discloses that work happens on owned copies with WAL handling, that source files are never modified, that output is bounded with truncation limits reported, and that consistency is reported while device atomicity is not inferred. These caveats are exactly the kind of context an agent needs before trusting the snapshot for comparison.

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?

Four front-loaded sentences, each carrying distinct information: purpose, safety/mechanics, a usage rule, and a caveat about limits. Slightly jargon-dense, but no filler sentences.

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 no output schema, the description does well to say what the snapshot contains and what limits/confidence signals it reports. But for a 6-parameter tool with a 17%-covered schema and no defaults documented, the description leaves the agent guessing about the budget parameters it must set.

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 17% — only analysis_project_id is documented in the schema. The description gives real meaning to paths (logical_root values so relative keys match) and implies that max_rows/max_files/max_total_bytes exist via 'bounded', but it never explains those caps, defaults, or truncation behavior, and label is unaddressed.

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 and resource: 'Create a bounded local snapshot of explicit acquired files/directories', and enumerates what the snapshot contains (hashes, preference XML, SQLite data). It lacks an explicit contrast with siblings like collect_storage_files, read_storage_snapshot or diff_storage, so the agent must infer the boundary from the word 'snapshot'.

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?

One concrete workflow rule is given: 'For before/after acquisitions use paths=[each acquisition logical_root] so relative keys match', which is genuinely actionable. However, there is no statement of when to prefer this over collect_storage_files or read_storage_snapshot, and no exclusions or prerequisites beyond the owned-copy assumption.

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