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

Annotations already flag destructiveHint=true, idempotentHint=true and openWorldHint=true, but the description goes well beyond them: secrets are preserved unless resubmitted, the type field is immutable, repeated delivery failures cause automatic disabling, and the call requires the `channels:manage` capability. These are exactly the operational facts an agent needs before mutating a channel.

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 purpose, then behavioral rules, then a per-parameter glossary, then a worked example — a logical progression with almost no filler. It is on the long side, but every section carries information not available in the structured fields, so the length is defensible rather than padding.

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?

A mutation tool with destructiveHint=true, no schema descriptions, and no enum hints — the risky categories — yet the description covers partial-update behavior, immutability, auth capability, auto-disable recovery, and workspace disambiguation. An output schema exists, so return values need not be described. Nothing an agent needs to call this safely is missing.

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%, so the description carries the full burden — and it does: channel_id (source: list_alert_channels), name (new label), url (https POST target for webhooks), recipients (full replacement list, not a merge), enabled (delivery on/off), and workspace (id, name, or `org-name/workspace-name` disambiguation, with default noted). The 'full replacement' wording for recipients is semantics the schema cannot express.

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?

Opens with a specific verb+resource ('Change a notification channel') and immediately enumerates the three shapes of change (rename, re-point, enable/disable), which cleanly separates it from create_alert_channel and delete_alert_channel in the sibling list. An agent can identify the tool's job without opening the 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?

Explicitly states partial-update semantics ('Only what you pass changes'), a hard exclusion with a redirect ('A channel's type cannot be changed — create a new one instead'), a recovery scenario (auto-disabled channels, pass enabled true after fixing), and points to list_alert_channels for obtaining channel_id. When-to-use, when-not-to-use, and the alternative are all present.

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