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

Annotations already declare the operation as non-read-only, non-destructive, and idempotent, so the description only needs to add behavioral context. It adds the important partial-update semantic ('Only provided fields are updated'), clarifies workspace-level scoping, and covers the edge case of annotating a company before lead linking. This is consistent with the 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 three sentences with no filler: the main action and partial-update behavior are front-loaded, followed by scope details and ID lookup guidance. Every sentence contributes useful information.

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 four-parameter update tool with no output schema, the description covers purpose, partial-update behavior, supported company scopes, and ID discovery. The main omission is lack of explicit return-value information, but the annotations and schema cover safety and parameter structure sufficiently.

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?

With schema description coverage at only 25%, the description carries a meaningful burden, and it partially compensates by naming the updateable fields (notes and tags) and explaining that only provided fields are mutated. It also tells the agent how to obtain companyId via get_company or list_companies. It doesn't fully detail every parameter, but combined with the schema's structural constraints, it provides enough semantic guidance.

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 uses a specific verb ('Update') and names the exact resource ('workspace-level metadata (notes and tags) on a company'), clearly distinguishing it from sibling tools like campaignstack_update_lead_metadata and campaignstack_update_workspace. It also communicates the partial-update behavior directly, leaving no ambiguity about the operation.

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 provides concrete usage context: it works for shared and imported companies, and a company can be annotated even before any lead links it to the workspace. It also explicitly directs the agent to campaignstack_get_company or campaignstack_list_companies for finding company IDs. However, it does not explicitly state when to prefer this over sibling update tools or when not to use it.

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