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

With no annotations, the description carries the full burden and does real work: it discloses budget routing (paid engines draw on Vendo's provider budget, LinkedIn hunters on the LinkedIn budget) and a per-contact cost of 5 credits, plus the wake-if-already-running behavior. It does not say whether the call blocks or returns immediately, nor what a failure looks like when the budget is exhausted.

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 dense sentences: behavior first, then the cost model, then the prerequisite call ordering. No filler, and the prerequisite is correctly placed last where an agent will read it just before acting.

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 ground-truth-free mutation tool with no annotations and no output schema, the description covers cost and ordering but leaves the return contract undefined — an agent cannot tell whether it receives run/job identifiers, a summary, or just an acknowledgement, which matters when monitoring kicked-off work via sdr_run_state.

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 50%: the source enum already documents that cross_pool and people_pool run automatically and cannot be started by hand, and the description only repeats that behavior. search_id has no schema description; "of a search" implies it identifies which search owns the hunters but adds no detail on scope or failure when the search is inactive.

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: starts (or wakes) one hunter or every enabled runnable hunter of a search. The scope distinction between a single hunter and all runnable hunters is explicit. It does not distinguish itself from near-siblings like sdr_resume_hunter or sdr_activate_search, only from the preview tool, so it falls short of a 5.

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?

"Call after sdr_preview_run_now" gives an explicit prerequisite and names the alternative tool to use first. It stops short of stating when not to call it directly (e.g. whether a paused or inactive search must be handled by sdr_activate_search / sdr_resume_search first).

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