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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive). The description adds real behavioral context beyond that: window and charts are plan-gated, excluded fields return null and appear in each item's `locked` list, `lockedCount` signals more results on higher plans, the agent must report the plan limitation rather than estimate, and the result is not rendered until sightglass_show is called.

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?

It opens with the payload, then usage triggers, then plan/locked semantics, then the show handoff – a sensible front-loaded order. It is dense but every sentence carries information; a little tightening of the locked-field sentence would help.

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 no output schema, the description does a good job describing the return shape (trend, launch and longevity charts, tech stack) and the locked/null/lockedCount contract, plus the two-step show workflow. It stops short of explaining pagination or limits, but nothing critical to correct invocation 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 description coverage is 100%, so the schema already documents days, weeks, companyRef, projectId and workspaceId with defaults and constraints. The description adds only the plan-capping idea for the trend/launch/longevity windows and the note that users say 'brands' for companies, which is marginal beyond the structured fields. Baseline 3 applies.

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 names the resource (one brand's advertising activity) and enumerates what comes back: daily active-ad trend, weekly launch counts, longevity buckets, and site tech stack with first-seen dates. That is specific enough to distinguish it from generic siblings like sightglass_get_company or sightglass_research_company, though it never names an alternative explicitly.

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?

It gives concrete triggering questions ('is this brand scaling up or pulling back', 'what did they change') and an explicit follow-up protocol: after getting the answer, call sightglass_show once with this call's resultId, and it notes the show call does not re-search. When-to-use and the downstream step are both spelled out.

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