diff_schema

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description reinforces rather than contradicts them ('Read-only — nothing is modified'). It adds the key behavioral context that the tool computes a hypothetical diff rather than mutating state. However, it does not disclose additional traits such as the version/vendor checks that the 'force' parameter bypasses or the structure of the reported operations. No annotation 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?

Two short sentences with the main action front-loaded immediately. The second sentence, 'Read-only — nothing is modified,' is somewhat redundant with the readOnlyHint annotation but serves as a quick safety reinforcement. No wasted words; appropriately sized.

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?

For a three-parameter, read-only diff tool, the combination of description and schema covers what agents need: the purpose, the safety profile (annotations), parameter semantics (schema), and the snapshot source (schema references get_schema_snapshot). A return-format note would add polish, but nothing essential to calling it correctly is missing.

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 100%: mode explains mirror vs merge semantics, force describes bypassing version/vendor checks, and snapshot references get_schema_snapshot as its source. Since the schema already carries full parameter documentation and the description adds no parameter-level meaning, the baseline 3 applies.

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 states a specific verb+resource pair ('Compare a schema snapshot against the current data model') and the outcome ('report what applying it would change'). This clearly distinguishes it from siblings like apply_schema (which performs the mutation) and get_schema_snapshot (which produces the snapshot input). An agent can tell it apart without opening the schema.

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 phrasing 'report what applying it would change' implicitly establishes this as a preview/dry-run step before apply_schema, and 'Read-only' signals it is not a mutator. However, no alternative tool is named explicitly, and the sibling list contains several adjacent tools (analyze_collection_schema, validate_collection_schema, get_collection_schema) with no differentiation. Usage context is clear but routing is left to inference.

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