check_fact_integrity

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does make clear this is a read-only check operation that 'Returns breakdown of source statuses,' which suggests no mutation. However, it does not disclose what happens for a nonexistent fact_id, whether the operation has side effects on source statuses, or any performance/runtime characteristics. The return type is named but its fields are not described.

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 economically formatted with standard Args/Returns sections. Every sentence serves a purpose, and the core action is front-loaded in the first line. It avoids fluff, though the 'Returns:' line repeats the already-stated 'breakdown' concept rather than adding new 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?

For a single-parameter tool, the description covers the input, the general behavior, and names the return type. It does not define what 'IntegrityCheckResult' contains beyond a 'source status breakdown,' and given the existence of three closely-related source tools, it could benefit from clarifying its scope relative to them. It is adequate but leaves ambiguity about what 'integrity' means operationally.

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 the schema only says 'Fact Id' with no description. The description compensates partially by stating 'fact_id: Fact UUID string,' adding that the value is a UUID and identifies the fact whose sources are checked. This adds modest meaning beyond the bare schema, but is thin — it doesn't state constraints on format beyond the label 'UUID string' or clarify what 'integrity' will be computed against.

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 states a clear verb+resource pair: 'Check integrity of a specific fact's sources.' It identifies the domain (facts and their sources) which helps distinguish it from unrelated siblings like list_tags or create_note. However, the term 'integrity' is vague without defining what metric is examined, and the tool's relationship to closely-related siblings (get_facts_with_stale_sources, revalidate_fact_sources, get_source_statistics) is not addressed.

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 provides no guidance on when to use this tool versus its closely-related siblings. There is no mention of when integrity checking is appropriate relative to revalidate_fact_sources (which presumably fixes sources) or get_facts_with_stale_sources (which identifies stale ones). No exclusions or alternatives are named, leaving the agent to guess which of the source-related tools to invoke.

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