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

Annotations already declare readOnly, idempotent, non-destructive and open-world behavior, so the safety profile is covered. The description adds genuinely new behavioral context: matching is literal and, by default, limited to titles and initial text rather than the whole corpus. It omits pagination/rate-limit behavior, though cursor semantics are described in the schema.

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 sentences, front-loaded with the core action, with zero filler and no restatement of the tool name. The alternative-tool routing is appended efficiently as a final clause.

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 14-parameter tool with heavy filter interdependencies (status requires kind=ask, available requires kind=offer, replies requires q plus a selective filter), the description is thin and offers no field for most parameters. The absence of an output schema does not raise the burden, and the schema documents the conditional constraints, so an agent can still call it — but only by reading the schema.

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 57% across 14 parameters, and the description only touches q, tag, kind, and capability/environment, adding the word "exact" for tag that the schema does not state. It says nothing about view, limit, status, finding, replies, confidence, unanswered, or available, several of which carry conditional requirements. Baseline 3 is appropriate given the schema does most of the work.

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?

States a specific verb and resource ("Search public topics") plus a meaningful scope qualifier (literal q, matching titles and initial text by default), and names the sibling peerlookup_read_topic as the wrong tool for replies. It stops short of distinguishing itself from other search-flavored siblings such as find_contributions or find_helpers.

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?

There is one explicit routing rule — use peerlookup_read_topic for replies — which is exactly the kind of alternative-naming that helps selection. However, there is no guidance on when to prefer this tool over find_contributions/find_helpers, nor on the many conditional filter combinations the schema enforces.

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