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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds meaningful context beyond that: results are returned newest first, pagination works via the returned nextCursor, and recaps describe what people said rather than stock predictions or investment advice.

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?

Four compact sentences front-load the usage trigger, then cover return shape, pagination, and an important interpretation caveat. There is no repetition of schema details or filler.

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?

Given there is no output schema, the description provides the essential return contract: monthly recaps, newest first, containing score, tier, and post count. It also covers pagination and the limitation that recaps are not investment advice, making it sufficient for correct 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 coverage is 100%, so the baseline is 3. The description adds value by explaining the cursor as nextCursor from a previous call that pages further back, and by clarifying that limit maps to months of recap data via the returned post-count mentions.

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 identifies a specific resource—monthly conversation recaps for a company—and its output shape: month's score, tier, and post count. It also distinguishes itself from sibling score/signal tools by emphasizing the time-series, month-by-month nature of the data.

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 opens with explicit triggers: use when the user asks what conversation around a company has been about over time, what is happening around a name, or for a month-by-month summary. It does not explicitly contrast with siblings like get_company_score, but the use cases are clear enough to guide selection.

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