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

Annotations already establish read-only, idempotent, non-destructive semantics, and the description adds what they cannot: the return is the raw CSS string, and it is an empty string when nothing is set. That empty-string detail is the key behavioral fact for the merge workflow, though nothing is said about size limits or formatting.

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 in the right order: what it reads, what it returns, and why to call it first. No filler and the read-before-write guidance lands last as the actionable takeaway.

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 one-parameter read tool with a full annotation set and no output schema, the description covers the field identity, the return value including the empty case, and the workflow role. Nothing an agent needs to invoke it correctly 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?

Single agentId parameter at 100% schema description coverage, so the schema already carries the semantics. The description adds no format, sourcing, or error behavior for an invalid ID beyond the schema's wording.

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?

Specific verb and resource: reads the agent's current customCSS field, with a parenthetical defining that field as the per-agent CSS override on the chat widget. It is unambiguously distinguishable from the write sibling update_agent_custom_css.

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 the use case ('Use this before editing so you can produce a merged result') and names the sibling it feeds into, update_agent_custom_css. It does not say when not to use it, e.g. that get_agent is the better choice when the CSS is not the focus.

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