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

The annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description adds the crucial detail those hints cannot: each supplied field is a FULL replacement list (not a merge), while omitted fields survive untouched — exactly the semantics an agent needs to avoid accidental data loss. It also discloses the timing effect (next daily search) that no annotation captures.

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?

Three sentences, front-loaded with the action and the field inventory, with zero filler. The middle sentence is dense — six fields plus per-field clarifications crammed into one clause — which slightly hurts scanability but does not waste words.

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 six-parameter mutation tool with no output schema, the description covers replacement semantics, field meanings, size limits, timing of effect, and what is explicitly out of scope. The only omission an agent might want is whether the call returns the resulting ICP state or just an acknowledgement.

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 0%, so the description must carry all six parameters, and it does: it clarifies watchProfiles as "LinkedIn public identifiers or profile URLs of competitors and creators" and watchKeywords as "phrases to search recent posts for", which are non-obvious distinctions. It also states the shape constraint (full list of up to 20 short strings) and the omit-means-unchanged rule.

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 opens with a specific verb and resource ("Replace any of the six targeting lists") and enumerates every field it touches: titles, industries, geos, keywords, watchProfiles, watchKeywords. That enumeration makes it trivially distinguishable from the read-only sibling get_icp, which shares the same ICP resource.

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 clear operating context: omitted fields are preserved, the next daily search picks up new values, and positioning/value proposition cannot be changed here because they regenerate from the product page. The one gap is that it never explicitly routes the agent to get_icp to read current lists before replacing them, so it stops short of naming alternatives.

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