Set the design source

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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, and the description usefully adds the replace semantic and that this carries authentication material (creds, sessionSettings, globalHeaders). It does not say whether an existing source's unmentioned settings are wiped, whether permissions/collector must be in place first, or whether testRequest is executed. The "replaces" wording sits slightly awkwardly against destructiveHint=false, but describes overwriting one sub-resource rather than deleting data, so this is a nuance rather than a contradiction.

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?

Two tight sentences with no filler; the action is front-loaded and the shape warning follows immediately. Field names are listed compactly inside parentheses rather than as padded prose.

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?

No output schema exists, so the description needn't cover returns, and it does explain the write target shape well. For a nested-object mutation with openWorldHint=true, however, it omits whether the design must pre-exist, what happens to prior source settings, and any credential-handling or permission constraints.

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 nominally 100%, but the source parameter is an untyped free-form object (additionalProperties: {}) with no declared properties, so the schema supplies almost no meaning. The description compensates substantially by naming the expected sub-fields (baseApiPath, collectorId, creds, sessionSettings, globalHeaders, testRequest) and warning against the export envelope's source.source shape. Types and required-ness inside source are still unstated.

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 and resource ("Creates or replaces the HTTP source") and even enumerates the sub-structures it writes: baseApiPath, collectorId, creds, sessionSettings, globalHeaders, testRequest. It does not differentiate from the sibling mpb_set_source_configuration, so the agent cannot tell from this text which of the two source-setting tools to pick.

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?

There is no when-to-use guidance, no prerequisites (does the design need to exist or already have a collector?), and no comparison to alternatives such as mpb_set_source_configuration or mpb_test_source. The only usage instruction is about input format (live GET /source shape rather than the export envelope), which is a call-shape rule rather than tool selection guidance.

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