add_item

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

With no annotations present, the description carries the full burden and largely does not meet it: it never says whether this creates a new record, what happens on a duplicate name, whether it persists immediately, or that an identifier is returned. It also omits the free-form `description` field entirely, so an agent cannot know that field exists from the prose.

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 one-line purpose is front-loaded, followed by a compact, scannable field-by-field block where every line adds an example or value domain that the schema lacks. The opening image ('before it vanishes') is slight flavour but it does convey the recall use case, so it still earns its place.

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 7-parameter creation tool with no annotations, the description covers 6 of 7 fields with usable examples and supplies the missing kind value domain plus the tags format. An output schema exists, so return values need not be explained. The residual gap is the undocumented `description` field and absent duplicate-handling behaviour.

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%, so the prose does the heavy lifting and mostly succeeds: it defines name, room, container, photo_hint with concrete examples and — critically — enumerates the valid `kind` values even though the schema declares no enum. It also specifies tags as 'comma-separated', which resolves ambiguity in the string-or-array anyOf. Deduction for leaving the `description` parameter undocumented and not marking which fields are required.

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?

"Catalogue one small thing" gives a specific verb (catalogue/create) and a narrow resource (a single small physical item), which clearly separates it from siblings like search, where_is, mark_moved and remove_item. The phrasing is slightly indirect — 'catalogue' rather than 'add' — but the intent is unmistakable.

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 statement of when to call this versus the alternatives, nor any exclusion such as how to handle an item that already exists (mark_moved/move_history are the obvious neighbours). 'Before it vanishes' hints at the recall/storage use case, but the agent must infer it from the purpose alone.

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