track_latent_skill

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

Annotations already declare readOnly=false, idempotent=false, destructive=false, openWorld=false; the description goes beyond them by explaining matching semantics (proposed/active candidates gain recurrence, otherwise a new proposed candidate is created), the project-scope initialization prerequisite, and the negative behavior 'Does not publish or generate skill files'. But 'not idempotent' largely repeats idempotentHint=false, and the returned fields are already covered by the output schema.

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 core action, then constraints, prerequisites, side effects, and next steps in a logical order. It is dense but nearly every clause carries distinct information, though the closing list of prohibitions and returns is slightly compressed into a run-on.

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?

Return values are summarized and an output schema exists, safety-relevant behavior is covered by annotations plus narrative, the initialization prerequisite is noted, and the follow-up path is spelled out. Nothing an agent needs to invoke this correctly is missing.

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%, so the schema carries the per-field burden and the baseline is 3. The description adds prerequisite context for the scope parameter ('Project scope requires initialization') and reinforces that evidence must be sanitized, which ties to evidence_summary beyond what the schema states.

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?

The description states a precise verb pair and object: 'Record curated evidence of a repeated workflow and create or increment a matching latent skill candidate.' It explicitly draws boundaries against sibling tools ('use remember_fact for preferences and create_skill for an explicit new skill request'), so an agent can identify the tool without opening any schema.

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 when-to-use ('Use only for recurring workflow observations'), explicit when-not-to-use with named alternatives (remember_fact, create_skill), a next-step recommendation (recommend_skills or propose_skill), and a prohibition on submitting secrets, raw logs, or transcripts as evidence.

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