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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description adds genuine extra context: perception_state of pending/unavailable/no_mentions means there is no value rather than zero, coverage must always be stated, and the semantic caution that cited sources are not the cause of criticism. That is real interpretive behavior beyond the annotations.

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 metric definition is front-loaded and the coverage caveat is well placed, but the two long, clause-heavy sentences (and the awkward 'sources cited alongside criticism, never its cause') reduce scannability for a read tool with a large parameter surface.

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?

No output schema exists, yet the description only sketches the shape of the response and says nothing about pagination via cursor/limit, what cohorts or views select, or how to pin a specific run. For an 11-parameter read tool this leaves the agent guessing at invocation.

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 9% across 11 parameters, so the description must compensate and largely does not. Only 'latest or a chosen run' hints at the audit_id/run selector; enum-bearing parameters (cohort core/comparison, view summary/quotes, theme, engine, polarity, entity, market_id) are left completely unexplained.

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 concrete verb+resource with the substance of what is returned (net sentiment -100 to +100, coverage, themes, quotes, sources) and scopes it to the latest or a chosen run. It reads as a distinct 'perception' reader, though it never names which sibling (e.g. read_visibility_results, read_query_evidence) it should be preferred over.

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?

'Latest or a chosen run' loosely implies when to call it, and the coverage caveat tells the agent how to interpret the result. There is no explicit when-to-use/when-not-to-use guidance relative to the many read_* siblings, so usage remains implied rather than stated.

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