write_skill

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

With no annotations, the description carries the full burden and does so: it discloses the destructive default (whole-file replacement unless append=True), explains the separate lifecycle of packaged vs. vault-stored content across upgrades, and states that changes take effect on the next read with no reinstall. That is exactly the behavioral context an agent needs before calling a mutation.

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-loads the action and location in the first sentence, then adds constraints in a compact block. A few phrasings are slightly mannered ('survive one', 'Nothing to reinstall'), but each sentence still conveys a distinct, load-bearing fact.

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 three-parameter mutation tool with an output schema, the description covers overwrite semantics, the permitted skills, and the effect on subsequent reads. Remaining gaps are minor: no guidance on failure behavior for an invalid skill name or whether content must be markdown.

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 description compensates: it enumerates the valid skill values (loci-save, loci-query, loci-inbox, loci-ingest-directory) which the schema does not, and explains the append flag's meaning against the default overwrite. The content parameter is only implied as the additions text, not explicitly characterized.

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: writing the user's additions to a Loci skill, and pins down the exact storage location (vault/skills/<skill>.md). It also identifies the counterpart tool read_skill and the section it manages, so the agent can distinguish it from generic vault writers.

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?

Gives a clear precondition — read the current additions via read_skill before rewriting — and an explicit alternative path (append=True for whole-file replacement). It also states what is not writable (the packaged procedure). It does not, however, contrast itself with sibling writers like write_vault or write_meta for an agent that might reach for a generic writer.

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