Get taste memory

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

Annotations declare readOnlyHint=false despite the name suggesting a pure read, and the description earns that distinction: 'If missing, regenerates the file from local engagement and anchors, including a configured vault mirror' explains the write side effect the agent would otherwise be surprised by. It also discloses output shape ('returns content and path') and that no model is invoked, which no annotation covers.

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?

Three sentences, zero filler, and the load-bearing information (what it reads, what it returns, and the regeneration side effect) is front-loaded before the sibling routing. Each sentence adds a distinct fact: purpose, alternatives, side effect/return.

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?

With no parameters, no output schema, and only lightweight annotations, the description carries everything needed: the artifact read, the mutation triggered on cache miss, the vault mirror touch, and the return pair. An agent can invoke it correctly and predict the side effect.

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?

The tool takes zero parameters and the schema has additionalProperties=false, so there is nothing for the description to disambiguate. Baseline for a 0-param tool applies; no value is added or lost.

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 — 'Read consolidated TASTE.md preferences and performance anchors' — which unambiguously identifies the artifact (TASTE.md) rather than a generic memory store. It then names the two nearest siblings (get_user_memory for hand-edited notes, update_user_taste for replacement) so an agent can distinguish this tool from them without opening either 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 states the positive use case ('use for writing or example-selection context') and supplies an alternative for each common misfire: get_user_memory when the agent wants hand-edited personal notes, update_user_taste when it wants to replace a section. This is when-to-use plus when-not-to-use plus named alternatives.

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