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

Beyond the minimal annotation (readOnlyHint: false), the description discloses significant behavioral traits: it runs real Python in a sandbox, cites and verification-badges every number, can join series from different agencies, returns a series_limit error when exceeding plan width, and requires an API key with a specific keyless error (key_required). This substantially exceeds the annotation's coverage.

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 longer than the calibration 'high' example but is densely packed with relevant information. Each sentence contributes to core understanding (what, how, constraints, comparison, authentication). It is front-loaded with the main value and uses semicolons to keep related ideas together, though it could be slightly more scannable.

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 tool's complexity and no output schema, the description covers most key aspects: process, time behavior, error conditions, auth requirements, and comparison to siblings. It lacks a detailed description of the report structure, but 'decision-ready report' gives a reasonable expectation. Overall, it is quite complete for an analysis tool, but a bit more output detail would make it fully 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?

Schema coverage is 75% (start, end, series have descriptions; question does not). The description adds meaningful parameter semantics by explaining the series joining across agencies and the series_limit cap tied to the caller's plan width. It also implies the 'question' parameter is the analysis prompt. This goes beyond the schema's simple type constraints.

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 uses a specific verb and resource: 'a PLANNED multi-section report on a question' and details the engine's behavior (designs 3-4 orthogonal analyses, runs Python, synthesizes one report). It clearly distinguishes from sibling tool 'answer' by stating 'use the answer tool for a single direct question.' This is a precise, differentiated purpose.

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?

The description explicitly states when to use the tool: 'use it for "analyze", "break down", "give me a full picture" asks' and when not to: 'use the answer tool for a single direct question.' It also provides contextual constraints like plan width limits and slower execution time (60-180 seconds), giving the agent clear decision guidance.

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