get_calibration_report

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the report contains a Brier score with 'lower=better' and a breakdown of resolved vs pending predictions, which adds value beyond the name. However, it does not explicitly state that the operation is read-only, nor does it disclose any potential side effects or limitations (e.g., whether results are cached or require specific permissions). This is a moderate gap.

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 two sentences long, with no fluff. The first sentence front-loads the purpose and specifics, and the second adds a useful interpretation of the report's significance. Every sentence earns its place, making it highly efficient.

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?

The tool has 3 parameters with no schema descriptions, no output schema, and no annotations. The description does summarize the output contents, which is helpful, but it fails to explain the role of any parameter. Without knowing how date ranges or source filtering work, an agent cannot correctly invoke the tool. This is a significant completeness gap.

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 explain the parameters. It only hints at 'source' via 'per-source accuracy,' but it does not directly explain what source, start_date, or end_date mean or how they affect the report. No format, defaults, or relationships are described. An agent would be left guessing how to populate these fields correctly.

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 clear verb+resource ('Get the signal calibration report') and then elaborates the exact contents: predictions count, Brier score, resolved vs pending breakdown, and per-source accuracy. It also states the purpose ('Shows whether Marketic's signal sources are reliable'), which distinguishes it from siblings like track_signal or collect_signals that focus on data ingestion rather than reporting. This is specific and unambiguous.

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 implies a use case: assessing signal source reliability, which is clear from 'Shows whether Marketic's signal sources are reliable.' However, it does not explicitly mention alternatives or when not to use this tool. Given the large sibling list, naming an alternative would strengthen this, but the context is sufficiently clear to guide an agent.

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