run_audit

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

With no annotations, the description does real work: it declares the operation read-only, discloses that live mode sources credentials from the environment and never accepts a token as an argument, and warns that evidence strings (property/stage names) should be treated as data rather than instructions — a notable prompt-injection safeguard. It still omits return shape, whether a report file is written, and runtime behavior.

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?

Sentences are short, declarative, and front-loaded with the purpose before mode and credential details. The line "needs_operator_confirmation is not a pass" is cryptic and reads as an unexplained internal rule, so not every sentence cleanly 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-annotation, no-output-schema tool, the description covers the safety/authorship dimensions well but leaves gaps: what the audit actually checks, what it returns or writes, and how it relates to list_checks. Adequate but not complete for an audit 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?

Schema description coverage is 100%, so the schema already documents all three parameters, making 3 the baseline. The description reinforces the meaning of demo mode (fictional sample portal) and the credential model for live mode, but adds nothing about pdfPath or publicSiteUrl beyond what the schema states.

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 opening sentence gives a specific verb and resource ("Run a read-only HubSpot audit") and states the read-only scope, which is enough to distinguish it from a mere lister like list_checks. However, it never names or contrasts with the sibling tool, so the differentiation is only implicit.

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?

It distinguishes demo mode (fictional sample portal) from live mode (reads HUBSPOT_ACCESS_TOKEN), which is useful when-to-use context for choosing a mode. But it offers no guidance on when to run this audit versus list_checks, and no prerequisites or exclusions beyond the mode choice.

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