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

Annotations already declare openWorldHint=true and destructiveHint=false, and the description adds genuinely new context beyond them: the operation is spend-bearing and requires an explicit confirm_spend_awt amount, the job is capped, and results are asynchronous requiring polling via jobs_get. Missing are idempotency semantics and whether wait_seconds blocks, but the cost-and-async profile is the most important disclosure for a mutating tool.

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 front-loaded clauses with no filler, and the workflow-relevant facts come first. The telegraphic style ('Quote first') is efficient but costs a little clarity.

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 an 8-parameter, no-output-schema, cost-bearing async tool, the description omits return shape, polling cadence, the meaning of wait_seconds and idempotency_key, and how this differs from research_search/research_read. It covers the spend gate but not enough to call it correctly and safely the first time.

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% across 8 parameters, so the description must compensate and it only names confirm_spend_awt. depth, max_sources, wait_seconds, required_claims, and especially idempotency_key receive no explanation at all, leaving the agent to guess at ranges and semantics from constraints alone.

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?

Specifies the verb and resource: multi-source research with citations, which is distinguishable from single-lookup siblings like research_search and research_read. It doesn't explicitly state the boundary versus those siblings, but the 'multi-source cited' qualifier does most of the work.

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?

'Quote first; confirm_spend_awt runs a capped job. Poll jobs_get.' gives an explicit two-phase workflow and names the follow-up tool for results. The gap is that the quoting step doesn't name which tool returns the quote, so the agent must infer that from the sibling list.

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