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

No annotations are supplied, so the description carries the full burden, and it does so: it discloses the cascading destruction list, that the campaign is stopped and deleted, that it is irreversible, and that there is 'no refund'. This is well beyond a generic delete warning and directly tells the agent what will be lost.

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 tight sentences ordered by importance: action and scope first, then irreversibility, then the approval prerequisite. No filler, and the destructive consequence is front-loaded.

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 one-parameter destructive tool with no annotations and no output schema, the description covers destructiveness, cascade, irreversibility, and the approval gate, which is enough to call it correctly. The only gap is not pinning down exactly what the 'id' refers to, which matters given the naming mismatch between 'delete_search' and 'SDR process'.

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% and the single 'id' parameter is a bare uuid, so the description would need to clarify what the id identifies (search id vs. process id, given the mismatch between the tool name 'delete_search' and the prose 'SDR process'). It does not, leaving the agent to infer from the tool name and the sdr_preview_delete_search reference.

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 ('Deletes the SDR process') and immediately scopes the blast radius by enumerating everything that goes with it (hunters, outreach campaign, signals, contacts, hunter state, QA runs, learning weights). The reference to the required sdr_preview_delete_search gate distinguishes it from sibling delete/pause tools such as sdr_pause_search and sdr_delete_outreach.

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?

Gives an explicit precondition — 'Only after the user approved sdr_preview_delete_search' — which tells the agent both the ordering constraint and the confirmation workflow. It does not, however, state the when-not case (e.g., use sdr_pause_search or sdr_delete_outreach instead when the user only wants to stop outreach), so the exclusion side is left implicit.

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