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

Annotations already declare readOnly/idempotent, and the description layers substantial extra behavior on top: plan gating returns nulls with a per-item `locked` list (`estimates` = sales, visits, traffic), `lockedCount` signals more results on a higher plan, and the agent must say data is on a higher plan rather than estimating it. It also discloses that the call returns data only and that nothing is shown to the user until sightglass_show, which is exactly the kind of non-obvious side effect an agent would otherwise miss.

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?

Purpose is front-loaded in the first sentence and every subsequent sentence carries real information (view list, plan-locking rules, show workflow, no-account note). It is a single dense paragraph with several run-on clauses, so structuring into distinct points would improve scanning, but there is little 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?

For a 6-parameter read tool with no output schema, the description covers the crucial pipeline (get data -> sightglass_show with resultId), plan-gating semantics, and auth independence. It falls short on the biggest remaining ambiguity: how to choose among the four named views, which is the primary thing an agent must decide before calling.

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 67% and the schema already documents groupBy's enum, projectId, categoryId and workspaceId. The description reinforces groupBy options and the categoryId drill-in, but it introduces view concepts (`pulse`, `share`, `categories`, `leaders`) that do not correspond to any parameter, leaving ambiguity about how to actually select a view, and it says nothing about `limit` or `weeks` boundaries beyond 'week by week'.

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?

It names a specific verb and resource ('who holds what share of active ads, week by week') and enumerates the sub-views (pulse, share, categories, leaders), which distinguishes it from siblings like sightglass_find_ads or sightglass_arena_compare. The only weakness is that those view names never map to a schema parameter, so the agent learns there are modes but not how to request one.

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 routing guidance: use `categories` to obtain a categoryId, then pass that categoryId to reach `leaders`; call sightglass_show once with the resultId to display; and it works before sign-in so it can be called before asking the user to authenticate. It lacks explicit 'when not to use this / use sibling X instead' exclusions for research-type siblings.

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