digest_output

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

No annotations are provided, so the description carries the full burden, and it does disclose substantive behavior: what is kept (first lines, error/failure/warning/test-total lines, last lines) and that the full text remains queryable via recall this session. It does not discuss side effects on existing memory, permissions, or size limits, so it is strong but not exhaustive.

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?

Front-loaded with the core action and an explicit breakdown of what is returned, followed by a compact Args section. Every sentence carries information; the Args block mildly duplicates the schema but adds the example and rationale.

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 two-parameter read-only-style tool with an output schema, the description covers purpose, return composition, and retention semantics. With no annotations, it could say more about session scope and side effects, but nothing critical to correct invocation is missing.

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 0% and both properties are bare, but the description compensates: text is identified as the raw output and label as a short recall key with a concrete example ("maven-build"). It adds real meaning beyond the schema, though it doesn't note the default value or label uniqueness.

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 (condense) plus resource (long command output such as build logs/test reports) and immediately clarifies the retention side effect. An agent can distinguish this from siblings like save_memory or recall because the description frames it as summarization-plus-retention rather than storing or fetching.

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?

Gives clear context: use it on long command output (build log, test report). It references recall("<label> ...") for later retrieval, letting the agent infer the workflow, but it names no explicit when-not or alternative tool for the same job, so it stops just short of 5.

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