manage_relationship

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

The description reveals important side effects for type=tag (edits file content, auto-creates tag) and workflow_member (upsert behavior), which goes beyond basic function. However, it lacks detail for agent_skill (no mention of side effects or permissions) and does not address reversibility or error cases for any type. With no annotations, the description carries the burden but is incomplete.

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 structured into an overview sentence followed by detailed explanation per type. It is efficient with no wasted words, though it could be slightly shortened by consolidating repeated phrases.

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 complexity of three relationship types and multiple actions, the description covers most behaviors for tag and workflow_member but leaves out details for agent_skill (e.g., what adding/removing entails). There is no output schema or error handling information, so an agent may lack full context to invoke the tool safely.

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 description adds meaningful context beyond the schema: for 'value' it specifies the format and that it writes as #<value>; for 'role' it states the default; for 'fileIds' it mentions a max of 100. Schema coverage is 91%, so the description enriches already well-documented parameters.

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 clearly lists the three relationship types (tag, agent_skill, workflow_member) and their actions (add/remove/share), making the tool's purpose explicit and specific for each case. It distinguishes itself from other tools by covering multiple relationship management scenarios in one tool.

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 when to use each type (e.g., for tags it modifies file content, for workflow_member it shares with an individual), but does not mention alternatives from sibling tools like share_create or share_revoke, nor does it provide explicit guidance on when not to use this tool.

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