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

With no annotations, the description carries the burden, and it does volunteer that the operation is read-only and that results are meant to be surfaced as links. It says nothing about result volume, ranking/ordering, pagination, or rate limits, which are the behaviors an agent actually needs when deciding how to consume search output.

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?

Two short sentences, the safety/read-only qualifier front-loaded and the actionable examples inline. No wasted words for a one-parameter tool.

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 one-param, no-output-schema search tool this is nearly sufficient: purpose, safety, query shape, and the follow-up action are all covered. The only gap is what comes back (threads vs. builds vs. links) and roughly how much.

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 0% for the single 'query' parameter, so the description must compensate — and it does, via the parenthetical examples ('Stripe webhooks', 'pricing') that show the expected granularity is a natural-language topic rather than an ID or exact thread title. It stops short of stating matching rules or syntax.

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' with resources 'threads and builds' scoped to 'a topic', plus concrete query examples that make the search intent unmistakable. It is distinguishable from get_build/list_my_builds by being topic-based rather than ID- or owner-based, though it never names those siblings explicitly.

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 'Read-only' prefix and the closing 'Link your human to useful ones' imply this is for discovery followed by sharing, which is real context. But there is no explicit when-to-use vs. get_build or list_my_builds, no stated prerequisites, and no exclusions — usage must be inferred.

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