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

Annotations already signal read-only, open-world, idempotent, and non-destructive behavior. The description adds meaningful behavioral context beyond those hints: it is a 'free read,' the weight uses a low prior as an anti-gaming cold start, and the data is historical/descriptive only. No contradiction with annotations.

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 and well-structured, front-loading the free-read nature before detailing the table's contents and workflow. The phrase 'Not financial advice' is redundant with 'never advice' and could be trimmed, but overall every other sentence earns its place.

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 zero-required-parameter read tool with an output schema, the description covers the returned fields, the anti-gaming semantics, the workflow, and the non-advice caveat. The main omission is the role of caller_id, which is optional and therefore low-impact but still technically part of the operation.

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?

There is one optional parameter, caller_id, with 0% schema description coverage and no mention in the tool description. The description does not compensate for the schema gap, leaving the agent to infer what caller_id means. It is optional and plausibly self-explanatory as a tracking identifier, but the description adds zero value for this parameter.

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 states it returns a source-effectiveness weight table and enumerates the specific dimensions and fields: per (source, signal_type, regime), graded counts, smoothed weight, fleet Layer-2 multiplier, and combined weighted value. It distinguishes itself from siblings like get_signal_effectiveness and get_source_accuracy by explaining the table's role as input to the composite effectiveness_weighted transform.

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 gives an explicit workflow: 'read alongside list_signal_catalog to pick streams with a real graded track record before authoring a definition.' It also sets an exclusion boundary with 'descriptive, never advice' and 'Not financial advice,' so an agent knows this is for selection context, not for generating advice.

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