Generate a paid SEO optimization proposal for a content draft using a query ID, optimization kind, and draft content. Review it before saving; spending permission is required.
Return a measured, paid optimization proposal. Does not save; requires spending:execute.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | Yes | ||
| query_id | Yes | ||
| project_id | No | ||
| draft_content | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.6.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full load, and it does disclose two important traits: the operation costs money (spending:execute) and is non-persistent ('does not save'). That is genuine value beyond the schema. However it omits the cost magnitude, whether the proposal is idempotent, and what determines the 'kind' measurement.
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, purpose front-loaded with constraints trailing. Nothing is padded, though the brevity contributes to the semantic gaps noted elsewhere.
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?
An output schema exists so return values needn't be explained, but the definition is incomplete for a paid, 4-parameter tool: no parameter meaning, no routing against the optimizer siblings, and no clarity on cost or side effects. An agent could invoke it without knowing what it will actually optimize or bill.
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 description coverage is 0% across 4 parameters, so the description is the only place semantics could be added. It says nothing about query_id, project_id, draft_content, or the seven enum values for kind (terms, header_terms, entities, fanout, structure, readability, style), leaving the agent to guess meaning entirely.
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 states it returns an 'optimization proposal,' which is related to but not clearly distinguished from siblings like run_content_optimizer and save_content_query_draft. It does not name the resource being optimized (draft content) or the verb's target, and 'measured' is vague. An agent gets the general idea but cannot confidently separate it from the optimizer family.
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?
'Does not save; requires spending:execute' states constraints but not when to use this versus run_content_optimizer or whether it should precede save_content_query_draft. No alternatives are named and no workflow context is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.