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

Annotations are all false and offer essentially no safety profile, so the description carries the full burden — and it delivers richly. It discloses the ~6-hour polling cadence, the past-24h relevance-sorted scope, the workspace-level uniqueness constraint, the fact that a conflicting watch is created but starts disabled, and the automatic ownership transfer on archival. This is exactly the kind of non-obvious runtime behavior an agent needs and could never infer from the schema or annotations.

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?

The description is longer than average but information-dense, with zero filler. It is logically structured: what the tool does, how the watch operates mechanically, the uniqueness constraint, the conflict edge case, and the pre-flight lookups. It is front-loaded with the core purpose, though the dense single paragraph without breaks is slightly harder to parse than it could be.

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 tool with this much behavioral complexity — background scheduling, uniqueness semantics, disabled states, ownership transfer — the description covers the operational landscape impressively. The only notable gap is return value: with no output schema present, an agent is left uncertain whether the call returns a watch ID, a status, or the lead-feed behavior confirmation.

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%: topicId and accountIds are documented in the schema, but campaignId has no schema description. The main description compensates by establishing campaignId's role as the target campaign receiving extracted leads, and it adds conceptual meaning to topicId (a keyword monitored on LinkedIn content search, relevance-sorted) that the schema's terse "ID of the topic to watch" lacks.

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 opening sentence states a specific verb and resource — "Set up a LinkedIn search watch that automatically discovers new leads for a campaign" — then precisely defines what a search watch is (monitors a topic keyword on LinkedIn content search, extracts post authors, feeds them as leads). This clearly differentiates it from sibling tools like create_competitor_watch, create_company_employee_watch, and create_signal_watch, which are all different watch types.

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?

The description gives explicit pre-flight workflow guidance: it names campaignstack_list_search_topics for checking already-watched topics and campaignstack_get_campaign_topics for topics on the target campaign, and explains the one-watch-per-topic constraint and the disabled-start fallback. It does not explicitly state when to choose this tool over the other watch-creating siblings, but the precise definition of what a search watch is makes the selection criteria reasonably inferable.

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