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

Annotations only declare readOnlyHint=true and openWorldHint=true; the description goes further by disclosing the shape of the returned explanation (value, status classification, canonical rule/version, winning source and rationale, lineage, evidence ids). With no output schema present, this carried disclosure is genuinely useful. It stops short of permissions, errors, or rate context.

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-loads the 'why' purpose, then two short usage sentences in a logical order with no filler sentences. The first sentence is a long enumerated list that is slightly dense but every item is informative rather than redundant.

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 3-param, no-output-schema, open-world read tool, the description covers purpose, output contents, and the special fact/source interaction. Combined with schema descriptions for slug and source, an agent has enough to call it correctly; only alternative-routing guidance is thin.

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 67% (fact has an enum but no description), and the description fills that gap by explaining that omitting fact lists explainable facts, and that fact=source.counted requires a source id. This adds operational meaning beyond the bare enum. slug semantics are left entirely to the schema.

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 ('explain') and resource ('a fact about one project') and enumerates what the explanation contains (value, FACT/DERIVED/UNKNOWN status, canonical rule + version, winning source, inputs, lineage, evidence ids). It is clearly distinct in intent from lookup-style siblings, though it never names a sibling to differentiate. Clear but no explicit sibling routing.

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?

Provides conditional usage for the fact parameter ('Omit fact to list what can be explained') and a usage note for source ('source.counted takes a source id'), which is real guidance. However, there is no when-to-use-this-vs-alternatives guidance relative to siblings like get_evidence or ask_hey, so usage stays at the implied level.

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