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

Annotations already declare destructiveHint=true and idempotentHint=true, so the risky-mutation profile is carried by structured data. The description adds the semantics of assign vs unassign and the 'me' shorthand, but never warns that a supplied description wholesale replaces existing text or that unassign removes people from a ticket — the most consequential behaviors here.

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 action, then a compact routing sentence for adjacent tools; every clause carries information. Slightly telegraphic ('by name ("me" for the user)') and the fragment structure takes a second read, but nothing is 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 5-param partial-update tool with no output schema, the description covers what changes, how assignment works, and which sibling handles each excluded operation. The remaining gap is the replace-vs-merge semantics of the description field and the irreversibility of unassigning, which belong in the description rather than only in the schema.

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 80%, so baseline is 3, but the description adds real meaning: assign 'adds people', unassign 'takes them off', and names may be given by name with 'me' resolving to the caller. Those complement the schema's positive-form descriptions of the two array params.

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 ('Changes a ticket's title or description, or who works on it') and enumerates the mutable fields. It explicitly carves out dates/priority and close/reopen to named siblings, so an agent can distinguish it from reschedule_ticket, close_ticket and reopen_ticket without opening schemas.

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 a clear partial-update rule ('Pass only what changes') and routes two adjacent operations to explicit alternatives. Missing any mention of how to obtain a valid ticket_id at call time (search_tickets/my_tickets only appears in the schema) and no guidance on fetching current assignees before unassigning.

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