opencdr_signals_search

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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description layers on real backend constraints: dedicated per-selector indexes that cannot be AND-combined, a max 31-day range, a 7-day default window, and silent ignoring of date params for some selectors. Those silent-ignore semantics are the kind of trap an agent cannot infer from structured fields.

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 short paragraphs, front-loaded with the verb and the single most important constraint (one selector). Every sentence carries actionable information, including the negative-space note about unsupported correlation fields.

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 9-parameter, no-output-schema, zero-schema-description tool, the description covers selectors, date semantics, pagination, and backend limits well. Gaps remain on limit/order behavior and on what a returned signal record looks like, though next_token signaling implies a paginated result envelope.

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%, so the description must compensate and largely does: it defines the mutual exclusion of severity/event_id/category/integration_id, the YYYY-MM-DD UTC inclusive format and 31-day cap on date_from/date_to, and pagination via next_token. Only limit and order, which have schema defaults but no stated meaning or interaction with next_token, go unexplained.

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 ("Search detection signals") and flags read-only up front. It distinguishes itself implicitly from opencdr_logs_search and opencdr_signals_stats by naming the 'signals' domain, but never explicitly routes to those siblings, so an agent must infer the boundary.

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?

Explicitly states the exactly-one-selector rule, names the four valid selectors, explains which parameters the date range governs and which it is ignored for, and documents an unsupported capability (correlation by source_ip/principal/resource/account/region) with the workaround (pivot via event_id). That is genuine when/when-not guidance.

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