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

Annotations already declare readOnly/idempotent/non-destructive, and the description confirms this ('read-only pull, safe to call freely') while adding genuinely new behavioral context: the cursor round-trip pattern, and the latency cadence (crawler near real-time vs daily research-run detection). The cadence disclosure is information no annotation or schema provides.

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 core purpose, then cadence, then an Args block. The Args list partially restates schema fields, but with 20% schema coverage that restatement is justified rather than redundant. Slightly verbose in the middle paragraph but every sentence conveys usable 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?

With no output schema, the description appropriately enumerates what the digest returns rather than leaving return shape unknown, and it covers cursor semantics, cadence, and defaults. The only gap is the undocumented user_intent parameter and the lack of explicit divergence from the get_notifications sibling.

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 only 20%, so the description carries the burden and does so well: it documents brand_id (required), since (ISO-8601, latest_seen semantics, omission behavior), days (1-180, default 7), and limit (1-200, default 50) with interaction logic ('days used only when since is absent'). It omits the fifth parameter user_intent, which is documented in the schema, so it's not fully complete.

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?

Front-loaded clause 'What changed for a brand since you last looked' gives a specific verb and resource, and the body enumerates exactly what the feed contains (visibility shifts, citations, competitor moves, rank changes, crawler signals, opportunities, reports). An agent can distinguish this activity-feed digest from siblings like get_latest_research or get_rankings.

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?

Explicitly describes the intended workflow: pair with the trakkr-watch prompt, capture latest_seen, and pass it back as `since` for incremental reads. It stops short of naming when NOT to use it (e.g. versus get_notifications or get_latest_research, which the 'same notifications' phrasing could overlap with), so it's strong but not fully differentiating.

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