whodb_platform_source_update

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds non-obvious nuance: the call changes nothing until the token is confirmed, and omitted config fields preserve existing values (partial-update semantics). That refines the destructive hint rather than repeating it. It still omits permission/auth requirements and whether the preview can be rejected safely.

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-loads the staging behavior in the first two sentences, which is the most decision-relevant fact. Four short sentences with essentially no filler; the workspace sentence is slightly bolted-on but 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 destructive, confirm-gated mutation with an output schema (the confirmation token), the description covers the safety-critical contract: staging, approval gate, and partial-update semantics. The gap is the six undocumented connection parameters, which no description sentence addresses.

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 only 33%: port, advanced, database, hostname, password, and username carry no descriptions anywhere. The description compensates partially by stating that omitted fields preserve existing hosted values, which is critical for credential fields, and clarifies per-call workspace targeting. One sentence cannot cover six undocumented params, so it lands at baseline.

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 ('Prepare update of a hosted WhoDB source') and the staging model, which distinguishes it from whodb_platform_source_create and whodb_platform_source_delete. It does not contrast itself with the generic whodb_platform_update sibling, but the scope is clear enough to select 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?

Gives explicit sequencing guidance: 'Do not call whodb_platform_confirm until the user approves the confirmation preview,' which tells the agent both when to call this and when to call the follow-up. It lacks an explicit when-not or a pointer to whodb_platform_source_config/test for inspection, so it stops short of full routing.

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