memory_crystallize

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 well: it discloses LLM usage, that it stores a crystal digest, attempts to save extracted lessons, and links source actions, plus the failure mode (missing or unfinished IDs fail) and the return shape {success,crystal}. This is exactly the side-effect and error context an agent needs for a mutation tool.

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 and effect, and every sentence contributes (mechanism, side effects, return value, error behavior, param format, usage routing). It is dense and slightly crammed in the parameter clause, but there is no filler.

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?

Despite having no output schema and no annotations, the description covers the return shape, mutation side effects, prerequisites (actions must be done/cancelled), and error conditions. Nothing essential for correct invocation 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 baseline is 3, but the description adds genuine meaning beyond the schema: actionIds is comma-separated and project/sessionId 'annotate the digest' rather than filter, clarifying these are metadata not selectors. It stops short of format examples for the IDs.

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 (summarize/crystallize) and resource (done or cancelled actions and their links) and explains the mechanism (configured LLM). It distinguishes itself from siblings by naming memory_lesson_save as the alternative path, so an agent can differentiate without opening another 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?

Explicitly scopes usage: 'Use for a completed work chain, not general recall' gives both the when and the when-not, and 'zero-LLM workflows should save curated lessons directly with memory_lesson_save' names the alternative tool and the condition that selects it.

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