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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds the default comparison window, but it does not disclose that output is capped by max_lines (default 400, max 5000) or how truncation manifests — a behavioral trait an agent calling this on large monitors needs.

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?

One front-loaded sentence with the core purpose first and the word_diff alternative after a semicolon; no wasted words.

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 6-parameter read tool with no output schema, the description covers the essential diff semantics but leaves out output truncation, what the diff looks like, and the meaning of the context parameter. Adequate to call it, not complete enough to predict its results.

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 67% and the description only restates the word_diff mode, which the schema already documents in detail. The two undocumented parameters, context and max_lines, get no explanation in either place, so the description does not compensate for the coverage gap.

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 ('Unified diff of one monitor between two of its snapshots') plus the default snapshot pair, which clearly separates it from siblings like get_snapshot, get_history, and list_snapshots.

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 this is the tool for comparing snapshots, and the word_diff clause gives one concrete when-to-use case ('better when a word changes in a long paragraph'). There is no explicit guidance on when to prefer get_snapshot or get_history instead, or on prerequisites such as having at least two snapshots.

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