annotate_session

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

With no annotations provided, the description must carry the full behavioral disclosure burden. It states the basic side effect—adding an annotation to the session timeline—but does not disclose whether annotations are persisted, whether they are immediately visible to 'get_annotations', whether adding is idempotent, or what happens on error. 'Add' implies mutation, but the consequences are left unspecified.

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 description is a single, front-loaded sentence that wastes no words. It names the action, the object, and the target while remaining easy to parse quickly.

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?

The tool has no output schema and no annotations, and the description does not explain the expected return value, side effects, or how this fits into the broader investigation workflow. An agent is not told whether the annotation concept is a crucial part of root-cause tracking or a lightweight note. Given the tool's moderate complexity (5 parameters, 1 enum), the description is minimally functional but incomplete.

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 80%, so most parameters already carry useful meaning in the input schema. The description adds no insight into the semantic roles of 'label', 'comment', 'category', or 'nodeId' beyond the existing schema descriptions, but it also does not need to compensate heavily. The missing parameter is the 'category' enum, which has no schema description; the description does not clarify when each category should be chosen.

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 uses a specific verb ('Add') with a clear object ('investigative annotation or hypothesis') and a destination ('session timeline'), which makes the core purpose immediately understandable. It does not explicitly contrast itself with the sibling 'get_annotations' tool, but the action is distinct enough that confusion is unlikely.

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?

The description gives no indication of when to use this tool versus alternatives. It does not mention that reads from the same timeline should go through 'get_annotations', nor does it state any prerequisites such as needing an existing session. An agent must infer entirely from the tool name that this is the write counterpart.

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