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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds nothing further — no summary length, style, determinism of output, or latency/cost expectations for what is effectively an LLM call. The '[inference]' tag hints at a model call but is unexplained.

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?

It is only a fragment, so there is no wasted text, but the brevity comes from under-specification rather than efficiency. There is nothing to front-load because no substantive information is present.

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 an inference-backed summarization call with no output schema, the description should say at least something about the shape or length of the returned summary and any input limits. Annotations cover the safety profile, but the operational expectations are entirely absent, leaving the agent to guess.

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?

There is one parameter ('text') and the description describes neither it nor any constraints. Schema description coverage is 0%, but the parameter name is self-evident and the schema supplies a concrete example input, so an agent can still infer what to pass. Baseline 3 is reasonable given the parameter is unambiguous, though the description contributes nothing.

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 string "[inference] Text summarization" restates the tool name and title without adding scope, such as input length limits, summary style, or target audience. It technically names a verb+resource, but nothing distinguishes it from the many sibling inference tools (inference, inference_stream, rag_augment) that could also transform text.

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 guidance, no exclusions, and no pointer to alternatives such as inference or inference_stream. At best the intent is implied by the tool name alone; the description itself gives the agent nothing to route on.

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