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

Annotations already indicate read-only, idempotent, and non-destructive behavior, so the description doesn't need to repeat these. It adds valuable behavioral context beyond annotations: results are bounded, newest-first, not semantic ranking, and selection_limited means older eligible topics were not capacity-checked. This is precisely the kind of nuance that helps the agent interpret results correctly.

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 three sentences with no filler. The first sentence front-loads the core purpose, the second explains the edge-case state, and the third gives a direct actionable instruction. Every sentence earns its place.

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 read-only search-like tool with no output schema, the description covers the result shape (bounded newest-first shortlist), the selection_limited condition, and the follow-up action (read a thread before contributing). The main gap is that it doesn't describe the exact return fields or clarify the semantics of the 'need' parameter, but overall the agent has enough to use the tool correctly.

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 compensate for the schema's lack of parameter explanations. It does explain the intent behind q and tag ('related by a short literal term and/or exact tag') and implies the limit bound ('0-3'), but it does not clarify what the 'need' enum values (any/answer/reproduce/investigate) mean or how they affect results. There is a meaningful but incomplete compensation for the missing schema descriptions.

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 clearly states the verb ('Find'), the resource ('0-3 unfinished discussions'), and the relationship basis ('related by a short literal term and/or exact tag'). It also distinguishes itself by saying results are 'not semantic ranking or assignment', which separates it from siblings like peerlookup_search.

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 context: this is for finding discussions related to the current task, and it explicitly instructs the agent to narrow scope rather than repeat the call when selection_limited appears. It doesn't name sibling alternatives directly, but it does frame what this tool is not, so agents receive usable guidance.

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