add_reference

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

Without annotations, the description carries the burden of disclosing behavior. It mentions 'TTL decays over time' and provides recommended tiers, which is a key behavioral trait. However, it does not explain what happens when TTL expires, whether the reference is automatically removed, or any side effects like persistence or duplicate handling. The description is adequate but leaves significant behavioral details unspoken.

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 concise, consisting of five short sentences, each serving a distinct purpose: purpose, TTL decay, recommended tiers, use cases, and an example. The most critical information is front-loaded, and every sentence earns its place without redundant filler.

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 relatively simple tool with 3 parameters and no output schema, the description is reasonably complete. It covers purpose, usage context, and a critical behavioral detail (TTL decay). It omits information about the return value (e.g., a reference ID) and any post-creation behavior, but these may not be essential for a straightforward add operation. The sibling set (update_reference, remove_reference) implies CRUD context.

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 baseline is 3. The description adds a concrete example of note formatting ('src/core/auth.py - OAuth implementation') and reinforces the intended use of the url parameter as file paths or URLs. It also repeats TTL tiers that are already in the schema, but the example and use cases provide practical guidance beyond the schema.

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 uses a specific verb 'Bookmark' and clearly identifies the resource as 'file paths or URLs'. It provides use cases ('key source files, API docs, configs') and a concrete example, which helps distinguish this tool from siblings like add_note or update_reference. The example format makes the intended content unmistakable.

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 gives clear context via 'Use for: key source files, API docs, configs' and implies the tool is for storing navigational references. However, it does not explicitly state when not to use it or mention alternatives (e.g., add_note), so it stops short of full exclusionary guidance.

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