record_observation

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

Annotations already declare this is a non-read-only, non-idempotent, non-destructive write. The description goes beyond that by disclosing that provenance fields are auto-filled from arguments, that `properties` overrides sugar defaults under a caller-last merge (D-02), and that the write routes through DeliveryAdapter.write() and a centralized provenance validator. That is genuine behavioral context an agent cannot get from the annotations, though the internal component names add little for invocation.

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, front-loaded with purpose, then mechanics, then the override rule. The 'D-02' ticket reference and 'DeliveryAdapter.write()' class name are internal jargon that does not help an agent decide or invoke, but the text is otherwise tight and waste-free.

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?

For a seven-parameter mutation tool with no output schema, the definition covers the write path and provenance handling but omits what a successful call returns (a handle? an id?) and says nothing about failure modes such as contract or validator rejection. Annotations cover the safety profile, so the gap is moderate rather than severe.

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 100%, so all seven parameters are already documented in the schema, which sets the baseline at 3. The description's note on the `properties` escape hatch and merge order largely restates the schema's own wording, adding no new per-parameter syntax or format guidance.

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: recording a new memory observation under a labeled MemorySink for a vault. It is distinguishable from read-oriented siblings like recall or search, but it never differentiates itself from the other write-side tools (write_note, supersede, update_frontmatter), so an agent must still guess which mutation path applies.

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?

The description explains mechanics but never states when to use this tool versus siblings such as write_note or supersede, nor any preconditions (e.g. that the vault must be registered, or that provenance fields are derived rather than supplied). Usage must be inferred entirely from the name and the required-parameter list.

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