compare_snapshots

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

The description explicitly states 'Reports arithmetic only, never whether a change was good or what caused it; read-only'. This goes beyond the schema and annotations (which are absent) by disclosing the tool's interpretive limits and safety profile. It tells the agent the tool will not provide causal or evaluative analysis, which is valuable behavioral context. It could add more about output format or error cases, but the core behavioral traits are well covered.

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?

The description is two sentences with no wasted words. The core action and compared fields are front-loaded, and the behavioral caveat ('arithmetic only... read-only') is placed at the end where it supplements rather than obscures the main purpose. Every sentence earns its place.

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?

The tool has an output schema, so return values are already structured. The description covers the tool's purpose, scope, and behavioral limits. It doesn't mention edge cases like what happens if a snapshot doesn't exist or if from/to are the same, but the schema's parameter descriptions and the output schema reduce the need for that. For a read-only comparison tool, this is nearly complete.

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%, so the schema already documents all three parameters thoroughly, including the special values 'latest' and 'previous' for from/to and the default/min/max for minImpressions. The description adds the list of compared fields, which gives context for what the parameters affect, but it doesn't add new parameter-level semantics beyond the schema. Baseline 3 is appropriate.

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 ('Compare'), a specific resource ('two snapshot documents'), and the exact fields compared ('clicks, impressions, positions, installs, ratings and locale counts'). It also distinguishes itself from siblings by focusing on snapshot comparison, which is unique among the listed tools. The scope is clear and an agent can select it 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 description implies when to use this tool: when comparing two snapshots and needing arithmetic differences. It does not explicitly name alternatives or exclusions, but the sibling list contains related tools like compare_search_periods and list_snapshots, and the description's focus on snapshots makes the usage context clear. It lacks an explicit 'use X instead when...' statement, so it doesn't earn a 5.

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