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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description still adds real value beyond them: ordering (newest first), pagination mechanics ('nextCursor for older months, null when there are none'), and a scope disclaimer that recaps describe conversation, not stock predictions.

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?

Three tight sentences: payload and ordering first, pagination second, scope disclaimer last. No redundancy with the title, and every sentence carries distinct 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?

There is no output schema, so the description carries the burden of describing returns, and it does: per-month summary, score, tier, post count, plus the pagination token. Nothing an agent needs to call or interpret this tool 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 100%, so baseline is 3. The description adds meaning beyond the schema by explaining that the cursor token returns 'older months' and by tying the returned nextCursor to the cursor input, which clarifies the pagination contract the schema only describes in isolation.

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 ('Returns month-by-month recaps of the tracked conversation around one company') and enumerates the payload (summary, score, tier, post count). The resource is clearly distinct from siblings like get_company_score and get_company_signals, so an agent can route without opening the 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?

Usage is implied by the content ('month-by-month recaps... newest first') rather than stated. It never says when to prefer this over get_company_score or get_company_signals, nor any exclusions, so the agent must infer the choice from the payload description.

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