distill

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the safety profile is covered. The description adds that other sessions can vote on entries and that export_distillates produces a curated jsonl bucket, which is useful lifecycle context, but it never explains non-idempotent behavior (duplicate submissions) or persistence/scope effects.

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 definition is short, front-loaded with the purpose, and uses compact value-set listings rather than prose. Every sentence contributes; the only minor cost is the terse fragment style around the optional fields.

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?

An output schema exists, so return-value explanation is correctly omitted. For a mutation tool with annotations, the description is adequate on kinds and confidence, but the undocumented memory_scope parameter and the absence of any usage routing leave gaps for a 5-parameter tool.

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 carry the load. It documents the allowed values for kind (6 options) and confidence (3 options) and marks source_thread optional, which is genuine added value the schema lacks (no enum is declared). But content is left unexplained and memory_scope, a 5th parameter with a meaningful default of 'project', is never mentioned at all.

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 verb phrase 'mark content as worth carrying forward' plus the enumeration of kinds (insight, pattern, anti-pattern, fix, terminology, concept) conveys the domain, so an agent grasps this is a knowledge-distillation record. However, the core action is abstract and the description never distinguishes distill from similarly-scoped siblings like note, lesson_append, register_concept, or tag_signal.

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?

It names related tools (vote_distill for voting, export_distillates for emission) but only as ecosystem description, not as routing guidance. There is no stated when-to-use, no when-not-to-use, and no comparison against the many sibling note/lesson/concept tools.

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