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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds substantial context beyond them: merge semantics ('fields passed are merged... omitted fields are left unchanged'), a permission restriction (read-only members cannot call), validation rules mirroring the retired form, and a visible side effect (company name on WeChat share cards).

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?

Front-loaded with the purpose, then conditions, then validation. It is dense rather than bloated, but the required-field rules and mode semantics are repeated between description and schema, costing a little efficiency.

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 5-param mutation tool with no output schema and no nested objects, the description covers everything an agent needs: merge vs. create behavior, per-mode required fields, validation constraints, permission gate, and the user-visible consequence. Nothing material is left to inference.

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 the baseline is 3, but the description earns extra credit by explaining non-obvious parameter behavior: company_name is the sole source of the share-card name, placeholder values like 'personal'/'test' are rejected, phone numbers and handles are disallowed, and industry must be from the listed enum. It clarifies conditional requirements without merely restating the schema.

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?

Opens with a specific verb and resource ('Record who this workspace is') and enumerates the exact content domain: company/org name, industry, share audience, and use case. No sibling tool competes with this purpose, and an agent can immediately tell this writes the workspace profile.

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?

Gives explicit when-to-use conditions: the retired web form makes this the only write path, and it spells out required fields per mode ('with usage=work, company name and industry are required; customer_type and use_case are required in both modes'). It also states the exclusion — read-only members cannot call it — and routes the personal case to usage="personal".

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