add_citation

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

Annotations declare it is a non-read-only, non-idempotent, non-destructive, closed-world write, so the safety profile is already covered. The description adds real behavioral context beyond them: that a citation handle is reusable across facts, that a citation carries a single confidence (so reuse must match the claim), and that source_title causes a new source AND citation to be created as a side effect. It does not say what the call returns (a handle id), which is the one remaining behavioral gap.

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 the core action, followed by the routing guidance and the positive use case. No filler, no repetition of schema content, and the most important sentence (don't call this directly) comes first.

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 single-object create tool with a fully documented nested schema but no output schema, the description covers purpose, routing, and side effects well. The only thing an agent might still want is what the call returns (the new or reused citation handle) so it can pass it to later calls, since no output schema supplies that.

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 the schema already documents every field, including the citation/source/source_title precedence rule. The description restates the reuse-vs-create distinction but adds no syntax, format, or constraint detail beyond what the CitationInput schema provides. Baseline 3 is appropriate.

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 ('Create a standalone Citation on a Source') plus the secondary mode ('or reuse an existing one'). The parenthetical immediately frames the two operating modes, and the following sentences distinguish it from the add_person/add_event_to_person/add_family siblings.

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 says when NOT to call it ('Usually you don't call this directly -- pass a CitationInput to add_person / add_event_to_person / add_family instead') and names the exact alternative tools. Then names the positive condition for calling it directly ('when you want a reusable citation handle to attach to several facts'). This is textbook when/when-not/alternatives routing.

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