skip_prospect

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

With no annotations provided, the description carries the full disclosure burden and exceeds expectations: it details the audit row write, the exact stamping formula (next_outreach_after = sentAt + noResponseRecycleDays), the effect on get_outbound_targets queries, plus explicit non-effects (no quota consumed, not marked contacted). This is model-level transparency for a mutation 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?

Two tightly packed sentences with zero filler. Every clause earns its place: the purpose, the side effects, the system interaction, and the key exclusion. Front-loaded with the action verb and clear object, the description delivers a full behavioral contract in under 60 words.

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 moderate-complexity 5-parameter tool with no output schema, the description covers all essential facets: purpose, side effects (audit row), state mutation (next_outreach_after stamp), temporal behavior (window), non-effects (no quota/contact), and edge-case exclusion (unsupported countries). Returning the skipped prospect's updated state or error semantics would be nice-to-have context, but nothing critical is missing—especially given the strong schema coverage on the more complex parameters.

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?

At 60% schema coverage, the schema already documents projectId, channel, and note reasonably well. The description alludes to domain concepts (noResponseRecycleDays, get_outbound_targets) that help the agent understand the tool's effect without fully mapping to individual parameters, but it doesn't add meaningfully beyond the schema—which is a fair trade given the existing annotation quality.

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?

Starts with a specific verb-phrase 'Record a deliberate skip' immediately followed by the resource ('a prospect on this outbound run') and a clear boundary ('no send is attempted'). It differentiates from siblings by explicitly stating 'no quota is consumed and the prospect is NOT marked contacted,' distinguishing it from record_outreach, while the one-window impact differentiates it from permanent actions like set_prospect_do_not_contact or delete_prospects.

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?

Provides an explicit when-not-to-use exclusion: 'Not for unsupported-country prospects — get_outbound_targets already filters those server-side,' which both names a sibling and explains why skip is unnecessary in that case. It lacks an explicit 'use alternative X for case Y' statement, but the behavioral framing (drops out of get_outbound_targets for that window) clearly implies when this tool is appropriate.

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