save_observation

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

With no annotations, the description carries the full burden, and it does disclose one genuine behavioral trait: missing data is explicitly marked rather than silently converted, plus the return shape (observation ID and provenance summary). It omits the write-specific traits that matter most here — whether saving is idempotent, what happens on duplicate source_record_id, and whether any validation or permission is required.

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?

Two short sentences, front-loaded with the core action, with no filler. The return-value sentence is somewhat redundant given an output schema exists, but the text is tight and readable.

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?

The output schema covers return values, so omitting them is acceptable, and the provenance framing is useful. However, for an 11-parameter write tool with no annotations, the description leaves the bulk of the contract — parameter intent, dedup/idempotency behavior, and validation expectations — undocumented.

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 schema has 11 parameters at 0% description coverage, so the description must supply the meaning — and it supplies none. Terms like source, raw_payload, system_name, pagination_cursor, coordinate_reference, and source_schema_version are left entirely undefined, including which are expected for which data_type. The one line about missing data being marked only loosely gestures at completeness_notes.

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?

"Save a provenance-tracked source observation to the research store" gives a specific verb (save) and a specific resource (provenance-tracked observation), and the target store is named. It implicitly contrasts with read-side siblings such as list_observations, but never names an alternative explicitly, so it stops short of a 5.

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?

There is no statement of when to call this versus alternatives (list_observations, eddn_live_sample, create_experiment), no prerequisites, and no note on whether repeated saves of the same observation are expected. Only the phrase "research store" hints at the workflow context, leaving usage entirely to inference.

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