run_audit

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

With no annotations, the description carries the full burden and does well: it declares read-only behavior, discloses the auth mechanism (env var, never an argument), and adds a prompt-injection warning about treating portal evidence strings as data. It omits rate limits and the fact that the tool writes a PDF report file, but the core behavioral profile is unusually well disclosed.

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?

Four short sentences, each earning its place, with the core purpose front-loaded and safety constraint last. Dense and waste-free, though the return-value/evidence remark is a fragment rather than an integrated statement.

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?

With no annotations and no output schema, the description should explain more about what the audit produces and its side effects; it only hints at output via "Evidence can include short portal property and stage names" and never mentions that pdfPath causes a report file to be written under reports/. Adequate for invocation, thin for outcomes.

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 coverage is 100%, so baseline is 3, but the description adds real meaning beyond the schema: it clarifies that live mode sources credentials from the environment and explicitly forbids passing a token as an argument — important given additionalProperties=false. The demo/live framing also contextualizes the demo flag beyond the schema's one-liner.

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?

States a specific verb+resource and scope: "Run a read-only HubSpot audit." This is clear enough to distinguish an audit-execution tool from the sibling list_checks, but the description never names or contrasts with that sibling, so the disambiguation is left to the agent.

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 explains the two modes (demo uses the fictional sample portal, live reads HUBSPOT_ACCESS_TOKEN), which implicitly tells the agent when each applies. However, there is no explicit when-to-use-this-vs-alternatives guidance and no statement of prerequisites or exclusions relative to list_checks.

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