presenter_labels

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

The description adds one genuinely useful behavioral fact beyond the readOnlyHint annotation: label assignment is stable for the lifetime of the server process ('the same value always gets the same label while this server runs'), which tells the agent that repeated calls are consistent and that state resets on restart. It does not clarify what happens to values not previously seen, or how the returned labels are structured. The phrase 'after adding values' hints at an internal registration step, which sits in mild tension with readOnlyHint=true, though it appears to be session-scoped in-memory state rather than an environment 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?

The 'Presenter mode:' prefix front-loads context well, but the single sentence is convoluted, stacking the purpose, the parameter shape, and the stability guarantee into one trailing clause. The information is all relevant; the packaging is denser than it needs to be.

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-optional-parameter read tool with no output schema, the description should make the return value unambiguous, and it does not — an agent cannot tell whether it receives a label, a map of value-to-label, or a list. The session-scoped stability note is good, but the output contract is left implicit.

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 description coverage is 0% and the schema itself only declares an array of free-form objects, so the description carries the full semantic load: it specifies the element shape ([{value, kind}]) and enumerates the valid kind values (connection / host / viya / user). That is substantial added meaning. It does not say what an omitted or null `values` returns, which is the remaining gap.

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 gestures at a concrete behavior: returning neutral stand-ins for identifying values (connection names, hosts, user names, Viya addresses) used in presenter mode. But the sentence is built around an awkward construction ('the neutral stand-in of every identifying value known so far ... after adding values') that leaves it unclear whether the tool returns a label map, registers new values, or both. An agent can guess the domain but not the exact operation.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no named alternative among the many sibling tools. 'Presenter mode' implies a context, but the agent must infer that this tool is only relevant when anonymized display values are needed.

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