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

Annotations already carry the safe-read profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial behavior beyond that: pagination rules (default 25, max 100, follow every non-null nextCursor with unchanged filters), that scanId must belong to this Site/Topic, that classification comes from the highest-confidence eligible mention, and that a removed identity can reappear.

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 core purpose before constraints, and each sentence carries distinct information (scope, exclusions, pagination, scanId semantics, promotion behavior). It is dense and slightly long, but there is little filler to cut.

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, return values need no explanation, and the description covers the remaining ambiguities an agent faces: what qualifies as a discovered entry, exclusion of tracking-off entries, pagination, scanId scoping, and the promotion path to add_competitor. Nothing essential 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 60%, and the description compensates meaningfully: it explains that omitting kind or passing [] includes unclassified entries (not stated in the enum), and that scanId narrows presence dates and Scans seen. Cursor and limit semantics largely duplicate the schema, but the added meaning for kind and scanId is real.

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 with a precise scope: entities with 'no configured roster membership' drawn from publication-ready Scans. This cleanly distinguishes it from siblings like list_competitors (configured roster) and add_competitor, so an agent can pick it without opening a schema.

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?

Names the follow-up alternative explicitly ('Use add_competitor to configure a selected entity') and clarifies what is excluded ('tracking switched off remain configured and are absent here', 'No automatic tracking'). It gives clear context for when this list is the right source, though it does not spell out exhaustive when-not conditions.

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