check_corpus_quality

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

readOnlyHint=true is consistent with 'returns a summary and the flagged documents only', and the description adds real value beyond annotations by enumerating the four damage classes detected and clarifying that output is filtered, not a full dump. It omits cost/latency expectations for scanning an entire corpus, which for a potentially long-running scan would be useful.

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 purpose and the damage categories are front-loaded and the prose is tight. The trailing 'Args:' block mostly duplicates the input schema's title and pattern, adding length without adding information.

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?

With an output schema present, the return-value gap is covered, and the read-only annotation covers the safety profile. What remains thin is the single undocumented parameter and the absence of any note on scan scope or duration for a corpus-wide check.

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%, so the description must carry the load, and 'agent_id: Knowledge Agent ID' only restates the schema title with a slight disambiguation (Knowledge Agent vs Jam). It does not explain the ID format constraint or where the agent ID comes from, but for a single required scalar parameter this is the minimum viable.

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 and resource ('find damaged documents in a Knowledge Agent's corpus') plus the deliverable ('recommended fix for each'). No sibling tool performs corpus quality inspection, so it is unambiguously distinguishable from list_documents, read_document, and get_document_status.

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 symptom statement ('Damaged text makes an agent miss topics its documents hold') implies a trigger condition, but the description never says explicitly when to run this, whether it should precede upload/ask_knowledge_agent, or whether there is any alternative to use instead. Usage is inferable rather than stated.

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