Manifesto Init

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

With zero annotations, the description carries the full burden; it does disclose the most important safety trait — that it refuses to overwrite an existing manifesto.json. It adds nothing about whether it creates the deck directory if absent, validation of the taxonomy fields, or failure modes, and the output schema covers the return value.

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 purpose is front-loaded in one clause and each remaining fragment maps to one parameter, so nothing is wasted. The telegraphic, colon-separated style is efficient but slightly clipped, reading more like a parameter legend than prose.

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 four-required-parameter scaffold tool with no annotations, the definition covers scope, all parameters, and the key non-overwrite guarantee, and an output schema covers the result. The remaining gaps are the derivation rule between campo_estudo and taxonomy_root and whether missing directories are created.

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 description must compensate, and it does: each of the four parameters gets a meaning and an example (absolute path for deck_dir, 'Medicina::Neurologia::ELA' for campo_estudo, 'ela' for deck_slug, 'ELA' for taxonomy_root). It stops short of explaining the '::' hierarchy convention or how taxonomy_root relates to campo_estudo, so the two taxonomy fields remain partly ambiguous.

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?

"Initialize a new manifesto.json for a deck" gives a specific verb (initialize) and artifact (manifesto.json) scoped to a deck, so the agent can distinguish it from manifesto_commit/import/state. It does not explicitly name which sibling to use instead when a manifesto already exists, so it falls short of full sibling differentiation.

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 definition implies the use case (a brand-new deck folder with no manifesto) and states a hard exclusion, "Will NOT overwrite an existing manifesto.json." However, it never says what to do instead when a manifesto already exists (e.g., which sibling to consult or mutate), leaving the routing decision to inference.

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