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

Annotations already declare readOnlyHint=true, and the description does not contradict that. The description adds valuable behavioral context beyond annotations: it discloses that the tool calls a local Ollama instance, uses the OLLAMA_HOST environment variable (with default), and that the model is configurable via ALMXPP_SUMMARIZE_MODEL. This external dependency and configuration info is important for an agent to anticipate behavior. It doesn't discuss failure modes, but the core behavioral traits are 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 description is compact and front-loaded: it opens with the 'WHEN' condition, then states the mechanism and configuration. Every sentence contributes either usage guidance or behavior transparency, with no filler. It is appropriately sized for a tool with only two simple parameters.

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?

Given the tool's simplicity (two params, no output schema), the description covers the essential aspects: when to use, what it does, external dependency, and configuration. It names example source tools, making the input type concrete. The only missing piece is explicit mention of the return value being plain text, but 'produce the summary' implies that. It is complete enough for correct invocation.

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 100%, so the baseline is 3. The description reinforces that 'text' is technical tool output and 'audience' relates to non-technical readers, but it adds no new parameter semantics beyond the schema's descriptions. The default audience and allowed values are already in the schema, so the description does not meaningfully increase understanding of the parameters.

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 clearly states the tool's function: taking large technical tool output and reframing it for a non-technical audience. It names specific sibling tools as example inputs (get_object_details, validate_best_practices), which distinguishes it from data-retrieval or analysis tools. The verb 'summarize' and the target audience are explicit.

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 begins with 'WHEN:' and specifies the exact condition: when you have large technical output that needs reframing for non-technical stakeholders. It names example source tools, giving agents concrete context. It does not explicitly state when not to use the tool or point to alternatives, but the trigger condition is unambiguous and the audience qualifier ('non-technical') implies exclusion of technical use cases.

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