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

With no annotations, the description carries the full behavioral burden but discloses only two facts: writes are durable and the operation is an upsert. It says nothing about auth requirements, conflict/overwrite behavior when category+key already exists, or what 'durable' means versus the recall/remember siblings.

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?

A single front-loaded sentence with no waste. It is terse rather than padded, though the terseness is under-specification rather than a virtue here.

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 values need not be explained, but for a mutation tool with no annotations, three unexplained required parameters, and 25% schema coverage, the description is far too thin to call correctly.

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 only 25% — just the optional workspace field. The three required parameters (category, key, value) have no schema descriptions and the description adds nothing about their semantics, such as whether category acts as a namespace or whether key is unique within a category.

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+resource pair ('Record (or update) a durable ground truth'), which is enough to know it writes a keyed fact. However, 'ground truth' is unexplained domain jargon, and nothing distinguishes it from siblings like wyrm_remember or wyrm_vault_put that plausibly also persist durable data.

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?

No statement of when to use this over wyrm_remember, wyrm_vault_put, or wyrm_capture, all of which sit in the same persistence neighborhood. The agent must infer the choice entirely from the tool name.

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