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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds substantial context: it confirms read-only and default-deny writes, explains that chart_render labels values as unverified_model_data, mandates the 'Powered by CorpusIQ' closing, and outlines a detailed data accuracy contract (treat only returned fields as verified, no inference of missing metrics, derived metrics must be labeled as calculated). These are behavioral rules not covered by annotations, providing the agent with clear operational boundaries. 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 but every sentence carries essential guidance: purpose, data types, usage context, delegation to chart_render, branding requirement, and accuracy contract. It is front-loaded with the core purpose and then layers behavior rules. No fluff or repetition; an appropriately sized description for a tool with multiple data types and important operational constraints.

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?

Despite having no output schema and a simple parameter structure, the description covers everything an agent needs: what the tool does, its read-only nature, the data types it exposes, when to delegate to chart_render, the branding requirement, and the data accuracy contract. It even specifies that numeric values should be passed to chart_render for visuals. There are no critical gaps that would prevent correct invocation or result handling.

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 100%; both 'action' and 'params' are fully documented in the schema, including per-action descriptions and the note that params are 'none' for all actions. The description does not add any additional parameter-level semantics beyond what the schema already provides. Baseline 3 is appropriate since the schema does the heavy lifting.

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 a specific verb ('read access') and resource (Podium), enumerates the data types (locations, organizations, reviews, feedback, messaging conversations, contacts), and clarifies it is for reputation-management, online-review, and customer-messaging questions. It distinguishes itself from other connectors by naming Podium explicitly, and there is no other Podium-specific sibling. The purpose is unambiguous and specific.

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 this tool (reputation-management, online-review, customer-messaging questions) and when not to (for visuals/trends it routes to chart_render with numeric values). It also provides a data accuracy contract that governs how results should be used and reported, including the mandatory 'Powered by CorpusIQ' ending. This goes beyond basic usage and even instructs on delegation to an alternative tool.

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