diff_storage

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: results may be truncated and snapshots may be inconsistent, and diffing is keyed on stable relative keys rather than absolute paths. It stops short of explaining pagination mechanics or ordering of before vs after.

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 dense sentence that front-loads the action and resource, then appends scope and caveats in descending priority. No filler, no restatement of the tool name.

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 useful work by enumerating the change categories and warning about truncation/consistency. Still missing for a 4-parameter analysis tool: how to source the snapshot IDs, whether before/after ordering matters, and behavior when a snapshot is missing or expired.

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 25% — only analysis_project_id is documented — so the description must compensate. It partially does: 'two retained storage snapshots' implies before_id/after_id are snapshot identifiers, and the mention of truncation hints at limit's role, but neither the 1-200 bound nor the ID format constraints are reinforced in prose.

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?

Specific verb ('Compare') plus a precise resource ('two retained storage snapshots') and an explicit comparison basis ('stable relative keys'), followed by the domains covered (file, XML preference, SQLite). It is clearly distinguishable from read_storage_snapshot or snapshot_storage, though it never names those siblings directly.

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?

Usage is only implied: the agent can infer it needs two retained snapshot IDs and that this is the diff counterpart to read_storage_snapshot. There is no explicit when-to-use/when-not, no guidance on obtaining the before/after IDs, and no statement about what to do if only one snapshot exists.

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