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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-structured behavior: that writes are deliberately unavailable here, how `period` overrides `days`, that only dashboard/metrics support periods, and that the response then carries a `period` block. Return-shape detail per view is lighter, keeping it at a 4.

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?

Front-loaded with the one-line purpose, then scoping constraint, then a consistent per-view list and an Args block, so an agent can scan to the exact knob it needs. It is longer than strictly necessary, with some prose (e.g., the narrative_drift entry) that could be tightened, but every section earns its place.

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 six parameters, a single enum, and no output schema, the description supplies enough to call the tool correctly and anticipates the main return shape per view (scores, themes, excerpts, period block). It does not describe pagination or result limits, which is a minor gap for a read tool of this size.

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 only 17%, so the description must carry the load, and it does: it documents brand_id (required), the full view enum with per-value meaning, days with its 7-365 range and 90 default, the YYYY-MM / YYYY-Qn period format plus its override behavior and view restriction, and tracked_brand's metrics-only scope. That is substantially more than the schema conveys.

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 ('Get brand perception analysis from AI models') and enumerates exactly what the analysis covers: sentiment, themes, narrative shifts, and competitive positioning. This separates it from siblings like compare_brands, get_narratives, and get_visibility_scores without the agent needing to open a 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?

Each of the five 'view' values is described with the condition that selects it, and the description explicitly rules out a workflow ('Refreshing perception is intentionally not exposed; trigger that from the dashboard'). It stops short of naming a sibling tool as the alternative for overlapping cases, so it is clear context rather than full when/when-not routing.

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