read_skill

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

No annotations are supplied, so the description carries the full burden, and it discloses two non-obvious traits: it works without a configured vault, and the user's additions only load once a vault exists. It stops short of stating side-effect profile (read-only) or whether the procedure text can vary per skill, but the conditional behavior is well covered.

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 definition, then the value list, then the vault caveat — a sensible order with little waste. The sentence "Answers without a vault too" is verbless and slightly cryptic, and the value list sits awkwardly between the two prose blocks.

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?

With one optional parameter and an output schema covering return values, the description supplies enough to call it correctly and to know how to treat the result. The main omission is per-skill meaning, which matters because the parameter is the sole input.

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 0% and the schema defines no enum, so the description's inline list (loci-save | loci-query | loci-inbox | loci-ingest-directory) is the only source of valid values — a substantial contribution. The gap is that it never explains what each skill does, so an agent can pick a valid value but not necessarily the right one; the default of loci-save is also undocumented.

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 ("Read a Loci skill") and clarifies what a skill is — "the packaged procedure with the user's own additions appended" — which an agent could not infer from the name alone. It is distinguishable from the sibling write_skill, though the distinction is implied rather than stated.

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?

"Follow the returned document for the whole interaction" is an explicit usage directive that frames this as an entry point whose output governs subsequent behavior. It also clarifies the vault-free case, but never explicitly contrasts with write_skill or says when NOT to call it.

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