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

With no annotations, the description must carry the behavioral load. It usefully discloses merge semantics for widget texts/theme and the 'Free' cost profile (no credit spend), which are not annotation-derived. It says nothing about permissions, whether changes go live immediately, or how errors surface for a multi-branch mutation.

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?

One front-loaded sentence names the verb and resource before the long parenthetical inventory, so the agent gets the gist first. The widget list is dense and run-on, but every clause maps to a real schema area 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?

For a nested, annotation-free mutation tool with no output schema, the description covers the major editable domains plus the key partial-update and merge rules. Residual gaps are the required-id sourcing and the boundary against sibling tools that own phone number/voice and Google Meet connection setup.

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?

At 57% schema coverage with 7 params and deep nesting, the description usefully enumerates the widget sub-surfaces (design, colours, button picture, invitation/auto-open, sounds, contact form wording, greetings, page navigation, voice view) that correspond to widget_config properties, and separates Meet settings from phone texts. The two required identifiers (id, connection_id) and their provenance are only in the schema, not the description.

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 opens with a specific verb+resource ('Change a channel') and then enumerates the concrete surfaces it covers (widget look/behaviour, name, website_url, Google Meet, phone texts), which lets an agent map it to the right schema branches without opening them. It does not name a sibling it is distinct from (e.g. create_agent_connection, setup_phone_agent), so differentiation is left to the name alone.

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?

'Only what you pass changes' tells the agent this is a partial-update tool rather than a replace, which is real usage guidance. However, there is no explicit when-not-to-use, no pointer to a read tool (get_agent_connection) before editing, and no mention that phone number/voice/inbound belong to a different tool — that routing hint exists only inside the schema, not in the description.

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