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

Annotations cover the safety profile (destructiveHint=true, idempotentHint=true), and the description adds substantial extra context: all-or-nothing batch semantics, that assigning replaces existing routing (reported as re-routed FROM the previous trunk), the null-to-unassign overload, and what the response contains. This is far beyond what annotations provide.

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?

A single front-loaded paragraph where each sentence carries distinct information (routing, accepted ids, unassign mode, atomicity, return shape). It is dense but no sentence is wasted; only the length of the single block slightly hurts scanability.

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?

With no output schema, the description proactively documents return contents (trunk name/type, assigned/unassigned numbers and count, re-routed reporting). Combined with atomicity and unassign behavior, an agent has everything needed to call it correctly.

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 the baseline is 3. The description adds real meaning beyond the schema: trunk_id accepts any type returned by list_trunks (SIP, PSTN, phone.systems, trunk group), and null/omit means unassign rather than a normal target.

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 (assign) and resource (DIDs → Voice IN Trunk) plus the routing consequence. It is clearly distinguishable from siblings like assign_did_to_sms_trunk and assign_did_to_capacity_group by naming the Voice IN Trunk target.

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 clear context: which trunk ids are acceptable, the null/omit path that turns the call into an unassign, and the max-100 batch constraint. It doesn't explicitly name the sibling assignment tools to steer between them, but the routing scenario is unambiguous.

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