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

Annotations already declare readOnly=false, idempotent=true, destructive=false, openWorld=true; the description adds real value beyond them: the permission model (manage/execute/prepare-proposal), the refusal set, and the retry semantics ('a repeated call with the same client_request_id returns the recorded action and does not run it again'). It also flags that upload_social_media and add_campaign_draft take media in the same call and how it is checked. The one gap is that it does not say how to discover valid action names or what a successful response looks like beyond the dedupe case.

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 core purpose, then auth, refusals, media, and idempotency in a logical order. It is a dense single paragraph but every sentence carries distinct information; only the long domain enumeration runs slightly long for a dispatcher.

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-value detail is not needed, and annotations cover the safety profile. The description supplies the permission gating, refusal scope, media handling and idempotency that a dispatcher's caller needs. It stops short of pointing to xora_action_details or xora_capabilities for enumerating valid action names, which would fully close the loop for an open-world registry.

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 75%, so the schema carries most of the load (action registry name, arguments passthrough, workflow_id, client_request_id). The description adds meaning the schema cannot: that 'arguments' are action-specific per each action's own input schema, the media parameters required only by two particular actions, and the replay semantics of client_request_id. This goes beyond 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?

States a specific verb+resource ('runs one settings action from Xorventa's own account API, by name with its arguments') and enumerates the domains it spans (chat window, Business Facts, knowledge sources, assistant, phone, mailbox, SEO, drafts). It explicitly refuses reads, publishing, sending and deleting, which cleanly separates it from xora_read, xora_publish_or_send and xora_delete without opening a schema.

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 concrete when-to-use conditions (connection holds xorventa:manage and the owner has allowed setting changes) and when-not (refuses reads/publishing/sending/deleting). It also names the escalation paths: xorventa:execute for always-confirm settings, or a proposal confirmed via xorventa:prepare — routing an agent to the right behavior on the ambiguous cases.

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