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

Annotations only include readOnlyHint=false and openWorldHint=true, so the description carries the burden of disclosing mutation behavior. It does so by listing mutating actions ('update', 'push') and adds the important caveat about mock results when credentials are missing. It also reveals return fields (resource_id, URL, signals, quality_score). It does not disclose failure modes or rate limits, but the available traits are transparent and consistent 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 compact (4 sentences) and front-loaded with the core purpose. It then logically progresses through mode breakdown, return value, mock behavior, and auth requirements. Every sentence adds useful information with no fluff, making it easy for an agent to quickly understand and invoke the tool.

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 tool with 5 parameters, nested objects, and an output schema, the description covers the primary use cases, auth requirements, mock behavior, and return values. It does not explicitly mention the async parameter, but the schema fully documents it. The description omits edge cases like partial failure or rate limits, but given the rich schema and annotations, it is sufficiently complete for effective use.

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%, so the baseline is 3. The description adds a high-level summary of the mode enum and mentions auth schemes, but the schema already documents the data payload structure per mode and the credentials object in detail. The description does not introduce new parameter semantics beyond what the schema already provides, hence a neutral score.

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+resource combination: 'Push, update, search and log activities in HubSpot, Salesforce or Pipedrive.' It then enumerates the 4 modes (push_lead, update_opportunity, search_contact, log_activity) with parenthetical clarifications (e.g., 'create contact/lead'), making the tool's purpose unmistakable. No sibling tool competes for this function, so the description fully distinguishes it.

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 clearly explains the 4 modes, implicitly guiding the user on which to use based on desired action. It also adds critical context: 'If credentials are absent, returns a mock result with a warning signal' and explains per-provider auth requirements. It does not explicitly state when not to use or name alternative tools, but the mode breakdown and mock-result warning provide strong contextual guidance.

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