Дифф страницы

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive. The description adds the critical behavioral constraint not in annotations: it diffs against a cached prior read and is meaningless without one. It doesn't discuss caching expiry or what happens when no cache exists, but the core dependency is disclosed.

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 WHEN/WHAT/NOT structure front-loads the deciding condition and packs scope, mechanism, and exclusions into three tight lines with no filler.

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 monitoring/diff tool the description covers the deciding context, the cache prerequisite, and the fallback, and an output schema exists so return values need no explanation. The only real gap is the undocumented max_chars parameter.

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 0% and the description mentions neither parameter. The required url is obvious from context, but max_chars (default 6000) is left entirely undefined in both schema and description, so an agent gets no guidance on the output-size knob.

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+resource ('дифф свежего чтения с прошлым из кэша') and explicitly frames what it produces ('что поменялось'). It cleanly distinguishes itself from fetch_page, so an agent can route without opening either 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 is organized as explicit WHEN / WHAT / NOT sections. It names the prerequisite (page already read), the exclusion (first read → fetch_page), and the alternative for full text (fetch_page). This is textbook routing guidance.

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