auto_structure_thought

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

With no annotations, the description carries the burden and does well: it discloses that this is a pure write to Firestore ('追加する', additive), that hierarchy depth is arbitrary rather than a fixed 3 levels, and that decomposition logic is the caller's responsibility, not the tool's. Gaps remain around what is returned (created IDs?) and behavior on partial failure or permission errors.

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?

Front-loaded with the core action, then the scope constraint, then the prerequisite routing in the final sentence. No sentence is redundant; every clause adds operational information.

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 an unannotated mutation tool with a rich nested schema but no output schema, the description covers the essential behavior (write-only, additive, arbitrary depth, existing-map-only, parent selection). It stops short of describing the return value or failure modes, which an agent would need for error handling and follow-up edits.

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 100%, so mapId, nodes, and parentElementId semantics are already documented in the schema (including the null/omitted = top level rule). The description adds only that parentElementId should be derived from list_elements output, which is procedural guidance rather than parameter-level meaning — baseline 3 is appropriate.

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+resource: appending a hierarchical structure of nodes into an existing map, with the explicit clarification that this tool performs only the Firestore write and no structuring logic. It also distinguishes itself from siblings by naming list_elements (for choosing the parent) and create_map (for new maps).

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 says when to use: existing maps only, and 'create_map first' when a new map is needed. It also gives the precondition for choosing parentElementId — look at list_elements results — so the agent knows which sibling to call before invoking this tool.

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