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

Annotations already declare readOnly, openWorld, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely useful method detail (footprint queries through web search, results merged by host), which implies deduplication behavior, but it says nothing about latency, result caps beyond limitPerAngle, or variability of open-world search results.

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?

A single dense sentence with the angles front-loaded and the mechanism trailing; every clause carries information and nothing is padded.

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?

There is no output schema, so the description must carry the return-value burden; 'merging the results by host' hints at the result shape but never states what a prospect record contains (URL, angle, host, why it matched). It is adequate for invocation but thin for interpreting results.

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 100%, so both parameters are already documented and the baseline is 3. The description adds no extra meaning for topic or limitPerAngle, such as what happens when the limit is hit or how a broad topic affects result quality.

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?

Specific verb (Find) plus a concrete resource (link-building prospects) with enumerated angles and the underlying method. It is clear the tool discovers candidate outreach targets, though it never distinguishes itself from the sibling find_competitor_link_sources, which reads as a near-neighbor.

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?

No when-to-use or when-not guidance appears. With siblings like find_competitor_link_sources and find_mentions in the same family, the description should say which situation selects this tool, but it gives no routing cues at all.

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