Configure the AutoSEO engine for a site

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

With annotations only providing false hints (readOnly, destructive, etc.), the description must and does carry the behavioral burden. It explains that approvalMode 'draft' routes to the pending-approval queue, 'auto' publishes unattended only with explicit opt-in, socialRepurpose never auto-posts and is off by default, and publicBaseUrl affects git_pr connector behavior. It also includes the CAPABILITY note that this creates content that cannot reach an audience on its own, adding safety information beyond 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 appropriately sized for a tool with 9 parameters. It front-loads the main purpose in the first sentence, then gives targeted detail for the most complex parameters (approvalMode, socialRepurpose, publicBaseUrl), and ends with sequencing. Every sentence adds value without redundancy.

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?

Given the tool's complexity (9 params, nested objects, no output schema), the description covers side effects, prerequisites, and safety. However, it does not describe the expected return value or confirmation behavior after a successful call, which would help an agent in a workflow with no output schema. Still, the behavioral and sequencing coverage is strong.

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 baseline is 3. The description adds meaningful context beyond the schema: it clarifies that approvalMode 'draft' is recommended/default, socialRepurpose is off by default with never auto-post guarantee, and publicBaseUrl only matters for git_pr connector. This is decision-guiding and adds value, but some nuance (like platform defaults) is already in the schema, so a 4 is appropriate.

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 clearly states the verb 'Set' and the resource 'the standing AutoSEO configuration for a connected site', enumerating all configuration areas (topics, cadence, backlinks, image style, approval mode, social repurpose). It distinguishes itself from sibling tools by naming the configuration scope and its sequencing role with autoseo_verify_site and autoseo_propose_topics.

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 explicit sequencing guidance: 'Call this after autoseo_verify_site confirms the site is live, and ideally after autoseo_propose_topics...' It also warns about approvalMode 'auto' requiring explicit user opt-in. However, it does not explicitly mention alternatives like autoseo_auto_configure or state when not to use this tool, so it stops short of full when/when-not coverage.

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