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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds the crucial context for why: it is a partial patch ('only the fields given change') whose supplied values overwrite prior text ('the previous text is replaced'). That distinction between additive and replacing semantics is exactly the behavior an agent needs before overwriting a persona. It stops short of stating permission requirements or what the response contains.

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?

Three short sentences with the editable field list front-loaded, followed by update semantics, then the scope exclusion. No filler, no repetition of the title.

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 five-parameter mutation tool with no output schema and annotations that already carry the safety profile, the description covers fields, replacement semantics and scope boundaries well. Minor omissions are the required agent_id reference and confirmation of what the call returns.

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?

With only 40% schema description coverage, the description does useful work by mapping the four editable fields and clarifying that persona means standing instructions. However, it never mentions agent_id (the sole required parameter) or the absence of a minimum-field constraint, so a call with only agent_id would be a silent no-op that nothing warns against.

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 (edit) and resource (agent) and enumerates exactly which fields it touches: name, role, description, persona. It also carves out scope by naming what it does not handle (capabilities, channels, approvals), which separates it from siblings like set_agent_status or update_agent_task without opening any 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 clear context for when this is the right tool and an explicit exclusion pointing elsewhere ('changed in Fine Structure') for capabilities, channels and approvals. The gap is that 'Fine Structure' is a UI concept rather than a sibling tool name, so the agent still has to infer which tool to call instead.

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