add_external_ref

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

No annotations are provided, so the description carries full burden. It transparently discloses that the tool only stores pointers and does not fetch external state — key behavioral context that prevents misuse. The only minor gap is no mention of idempotency, overwrite behavior, or what happens if the ref already exists, though the 'stores pointers' framing covers the core constraint.

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 sentences, zero waste. The first sentence states the action with example systems, the second delivers critical caveat and alternative guidance. Every word earns its place.

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 simple 4-param tool with 100% schema coverage and an output schema, the description fully covers purpose, limitation, and usage alternative. The tool is straightforward (store a pointer), and the description handles it completely.

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 coverage is 100%, so the schema already describes all 4 parameters well. The description adds value by framing what the stored data represents (a pointer to external state) and clarifies the semantic intent: this is for cross-system references. The description does not list params in prose, but the schema is thorough (including the optional url with default), so the baseline holds with minor added context.

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 states the verb+resource: 'Attach a reference to an external tracking system' with explicit examples (Jira, GitHub). The first sentence is concise and specific, and it distinguishes from sibling tools like remove_external_ref, which handles the inverse operation.

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 explicitly states when NOT to use this for fetching state: 'ContextForge does not fetch these — it just stores pointers. Use a separate MCP server (Atlassian, GitHub, etc.) to retrieve current state.' This is excellent guidance on the tool's limitations and points to alternatives for the broader workflow.

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