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

With no annotations present, the description carries the burden well: it declares read-only, enumerates the status lifecycle (queued/running/done/error), describes stages/events, and says when the result payload appears. It stops short of explaining failure/retry behavior or how long a job_id remains pollable after completion, which matters for a polling 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?

Front-loads the safety signal ('Read-only'), then identifier usage, then return shape, then cadence — a natural call order. The parenthetical lists are dense but each clause carries information an agent needs; nothing is filler.

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?

No output schema and no annotations exist, so both burdens fall here, and the description enumerates the dossier plus the editable profile fields returned on completion. Combined with the polling interval, an agent has everything needed to call and re-call it 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 coverage is 0%, so the description does the work: it explains where job_id comes from and the two distinct conditions for agent_id. The remaining gap is that neither parameter is required (0 required), and the description never states whether exactly one must be supplied or which takes precedence if both are passed.

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 ('Poll an SDR ICP research'), and explicitly frames itself as the read-only counterpart to sdr_start_research. An agent can distinguish it from sdr_get_search, sdr_run_state, and sdr_start_research without opening any schema.

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?

Names both entry paths (job_id from sdr_start_research or a prior poll; agent_id while the profile is still building) and gives the polling cadence ('every 5–10 s'). The when-to-use condition for each identifier is spelled out rather than inferred.

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