propose_skill

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

Annotations declare a non-read-only, non-idempotent, non-destructive mutation, and the description supplies the context they cannot: candidate state is mutated through a 'safe pipeline', a genuine project-memory prerequisite exists, and 'inspect state before repeating a decision' warns against blind retries given idempotentHint=false. The only soft spot is the undefined phrase 'safe pipeline', which is a minor gap against otherwise rich disclosure.

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 purpose, then usage, then prerequisites, then decision semantics – a sensible ordering for an agent scanning for go/no-go signals. It is dense with semicolon-chained clauses and repeats the decision vocabulary already in the schema, which costs some tightness.

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 two-parameter mutation gated on project initialization, the description covers workflow position, prerequisites, all decision values, the no-decision review path, and a retry caution, while the output schema and annotations already carry return shape and safety profile. An agent has everything needed to call this correctly on the first attempt.

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 100% and both parameters are already documented, so the description's restatement of yes/y accepts, no/n ignores, and always records future approval policy largely duplicates the schema text. The one genuinely additive note is that an omitted decision returns a proposal plus follow-up choices, which extends beyond 'omit to review only'.

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: review a tracked latent workflow candidate or record a decision about it. It immediately distinguishes itself from create_skill and ties itself to the track_latent_skill/recommend_skills pipeline, so the agent knows exactly which stage of the workflow this tool occupies.

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?

Explicit upstream dependencies ('use after track_latent_skill or recommend_skills'), an explicit exclusion routing to a named sibling ('use create_skill for an explicitly requested new canonical skill'), and a hard prerequisite ('requires initialized project memory and a latent candidate ID'). Nothing about when to reach for this tool is left to inference.

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