intel_brief

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

With no annotations, the description carries the burden and does well: it discloses the convergence rule (link_km, >=2 domains or a single critical/high signal) and what each ranked incident contains (narrative, threat_level, evidence with IDs, recommended queries). It stops short of stating it is read-only/side-effect-free, or any latency/cost characteristics, which would be the remaining behavioral gaps.

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-loaded with the headline purpose, then the convergence definition, then usage — a sensible information hierarchy. The 'instead of returning signals you have to correlate yourself' contrast is a touch of salesmanship but serves differentiation; overall every line does work.

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?

Output schema exists, so return values needn't be re-explained, and the description covers scoping and the convergence rule well. But for a 10-parameter tool with 0% schema coverage and no annotations, it leaves detail mode, window_hours, and radius units unaddressed, so an agent cannot fully reason about all inputs from the description alone.

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% across 10 params, so the description must compensate. It meaningfully explains lat/lon as a centre, the bbox alternative, and gives real semantics to link_km (the convergence distance). However, it leaves window_hours, detail, and the NM unit for radius_nm undocumented, so roughly half the parameters remain opaque.

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 ('fuses raw layers into ranked, cited INCIDENTS') and defines the core abstraction (a CONVERGENCE of signals across >=2 domains). It explicitly distinguishes itself from drill-down siblings by naming query_vessels, gps_jamming, and deep_analyze as the tools to reach for after the brief.

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?

Explicit when-to-use guidance: 'Start here, then drill into...' names the entry point and the follow-on alternatives. It also gives concrete scoping rules — omit coordinates for a global brief, or pass centre+radius or bbox to scope it.

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