essay.shelf.put

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

With no annotations, the description does carry the full burden, and it discloses the mutation target path, that scope is sequence-local rather than module-wide, and that a confirm phase is involved. It does not say whether an existing shelf entry is overwritten, what confirmPhase controls, or what permissions/errors apply — meaningful gaps for a write tool.

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 and short, with the scoping constraint and path stated early. However it is written in telegraphic fragments, and the closing imperative 'Say the draft path to the user' is an output instruction rather than tool behavior, which muddies the structure.

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 mutation with a nested open object, no annotations, no output schema, and a two-step confirmation workflow, the description omits the confirm-phase semantics, overwrite behavior, and return shape. It is not sufficient on its own for an agent to invoke this correctly without inspecting the schema and sibling tools.

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% across 5 parameters, so the description must compensate. It adds genuine meaning for essay_id (it is a sequence id, local to that sequence) and implies pack must be Word-confirmed, but pack (an open nested object), pack_id, topic, and confirmPhase are left entirely unexplained.

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 concrete verb and resource: it stores a Word-confirmed pack onto a specific sequence shelf, with the literal path template (Essay-writer/<module>/sequences/<n>/shelf) and an explicit exclusion ('not on the module root'). This distinguishes it from a generic save and hints at the read counterpart essay.shelf.get, though the term 'Word-confirmed pack' is domain jargon that isn't defined.

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 parenthetical '(Confirm two-step)' and 'Word-confirmed' imply a prerequisite workflow — the pack must first be confirmed via essay.pack.validate/render_word before this call — but no sibling tool is named and no when-not condition is given. An agent can infer sequencing but must guess which tool produces the required input.

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