whodb_platform_ontology_similar

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so safety is covered structurally. The description goes beyond by disclosing that the platform returns an explanatory error when embeddings are not ready, and by clarifying that per-call workspace targeting does not change session defaults.

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 purpose, then prerequisites and the recovery action, then workspace targeting. Each sentence earns its place, though the workspace sentence is somewhat dense and could be trimmed since the schema already covers it.

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 read-only similarity tool with full schema coverage and a rich nested workspace object, the description supplies the key non-schema facts (embedding prerequisite, error behavior, reembed recovery, non-defaulting workspace). With no output schema, it doesn't describe return shape, but the role is otherwise fully covered.

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 every parameter including the nested workspace fields is already documented in the schema. The description restates the workspace {host, org, project} targeting and its default-vs-override semantics, adding only marginal value over the schema baseline.

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?

The description names a specific verb and resource ('Find rows similar to one row using the ontology's embeddings'), which is immediately distinguishable from sibling read tools like ontology_query or ontology_rows. An agent can tell what this does without opening the 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?

It states clear preconditions (embeddingEnabled on the ontology, completed embedding job) and the failure behavior, plus routes the agent to whodb_platform_action reembed to start a backfill. It stops short of explicitly contrasting this with the other recall/lookup siblings (e.g. fast_lookup, ontology_query).

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