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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description adds real behavioral context on top: results carry provenance and primary evidence, and sparsity in the output is not proof of unavailability — a genuinely useful warning about data completeness.

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 dense sentences, front-loaded with the core operation and ending with the most actionable caveat. The phrasing is jargon-heavy ('aggregate membership changes') but nothing is redundant.

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 read-only diff tool with no required parameters and no output schema, the description covers the nature of the output and a key caveat, but leaves both parameters and the shape/size of a 'change' row unexplained.

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% for two parameters. Neither 'limit' (1-100, default 50) nor 'gpuModel' (a bare string with no description) is explained in the description, so the agent gets no help on what gpuModel matches or how limit affects the diff.

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 identifies a specific resource and operation: dated price, availability and membership changes computed between 'real GPU observations,' with provenance and evidence. An agent can tell it is a diff/delta tool rather than a snapshot, though it never names gpu.history or gpu.board to sharpen the distinction.

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?

There is no when-to-use statement and no comparison against the obvious siblings gpu.history and gpu.board. The closing line ('A missing row does not prove unavailable capacity') is an interpretation caveat about the returned data, not guidance on selecting or invoking this tool.

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