get_annotations

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

With no annotations, the description carries the full burden. It usefully discloses that page-wide scans are paged (default limit 100) and that includeCategories defaults to false, which is real behavioral context. It says nothing about ordering, output shape, or failure modes, so the disclosure is helpful but incomplete.

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 front-loaded sentences that each carry actionable information: scope, paging, and parameter routing. No filler, though the includeCategories note is somewhat parenthetical.

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-parameter read tool with no output schema and no annotations, the description covers scope selection, pagination, and a key default. The one real gap is the undocumented offset parameter, which no structured field compensates for.

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 60%, with nodeId and offset undocumented in the schema. The description compensates by explaining that nodeId targets one node and rootNodeId scopes to a subtree, and by clarifying the includeCategories expansion behavior. offset remains undocumented in both places, keeping it below 5.

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 and resource (get annotations) plus scope (a node or a subtree), so an agent can distinguish it from the setter siblings set_annotation and set_multiple_annotations. It does not, however, name or contrast with those siblings explicitly.

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 parameter routing: 'Pass nodeId for one node, or rootNodeId to scope.' That tells the agent how to choose between the two mutually exclusive scoping paths. It offers no explicit when-not guidance or comparison against alternative read tools like get_node_info.

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