source

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description lists remove_citation, remove_web_link, and unlink_repository, which are destructive operations, consistent with the annotation. It also adds workflow context like webLinkId coming from person.get. No contradiction; the description adds action-level behavior beyond the annotations.

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?

The description is comprehensive but long; it uses a clear structure with a definition, a list of actions, and specific workflow pointers. It is front-loaded with the core concept. Though verbose, each sentence adds value, so it is acceptable.

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?

Given the tool has 12 actions and 26 parameters with no output schema, the description should explain each action's purpose and parameter implications. It lists actions but leaves many as self-explanatory, and it provides some hints (e.g., get_citation returns facts). However, details for actions like link_repository, update_citation, and add_web_link are not fully elaborated, making the definition incomplete for reliable invocation.

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 15%, and most parameters (url, date, note, page, email, phone, etc.) are not explained in the description. The description only hints at a few parameters (e.g., create_source requires title, create_citation requires sourceId and detail). This is insufficient compensation for the low schema coverage, leaving many parameters ambiguous.

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 begins by defining what a source versus a citation is, then lists the exact actions available. It clearly states the tool manages sources, repositories, citations, and web links, distinguishing it from siblings that handle persons, facts, or trees.

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 provides workflow guidance: create_source takes only title, then update_source fills details; create_citation needs sourceId and detail. It references fact.attach_citation and person.get, indicating how the tool fits the overall process. However, it does not explicitly state when to prefer this tool over a sibling or when not to use it.

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