assess_signal

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

The annotations indicate idempotent and destructive (side-effect) behavior. The description adds crucial context: token costs (5/15), charging to key owner's balance, caching of prior assessments, and rejection of not-observable signals before any charge. It also details the result's context block, fulfilling transparency beyond structured data.

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?

The description is dense but every sentence carries information: purpose, result contents, cost, caching, and pre-filtering instruction. It is somewhat long but appropriate for the tool's complexity; no filler or repetition.

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?

Given the rich output schema (context block, meta.tokens) and the description's coverage of inputs, outputs, cost, caching, and rejection behavior, the tool is fully specified for an agent to select and invoke it correctly. It even tells the agent the follow-up action (pass imagery_handoff to search_imagery), making it self-contained.

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?

The schema already documents both parameters with 100% coverage, so baseline is 3. The description adds cost semantics for kind (quick=5, deep=15 tokens) and clarifies eventId as coming from query_signals, though the latter repeats schema. This extra context raises it to 4.

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?

The description opens with a specific verb and resource: 'Run an AI RS deep-dive assessment for a specific signal: what to observe, recommended sensors, and a collection window.' It clearly distinguishes from siblings like query_signals (listing signals) and search_imagery (finding imagery) by emphasizing the analysis and actionable plan output.

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?

It provides explicit usage guidance: signals not satellite-observable are rejected before charge, so it instructs to pre-filter with query_signals observability:'observable'. It also states the result carries an imagery_handoff to pass to search_imagery, giving the agent a clear workflow. While it doesn't list alternative assessment tools, it gives a when-not-to-use condition, meeting the bar.

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