track

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

With no annotations, the description carries the full burden, and it does disclose one meaningful behavioral trait: the source is 'journaled; survives restarts,' which tells the agent changes are durable. It omits other relevant behavior such as duplicate handling, validation failures, or what happens when an unknown source_id is passed.

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?

Front-loaded with the action and the key durability fact, followed by concrete seed examples. Efficient overall, though the hardcoded seed list is arguably instance data that could live elsewhere.

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 one-parameter registration tool with no output schema and no annotations, the description covers purpose, durability, and ID format examples. Missing only edge-case behavior (duplicates, invalid IDs) and return semantics, which keeps it just short of complete.

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 0% for the single parameter, so the description must compensate. The seed set examples reveal the required ID convention (namespaced values like 'project:tsavkisi-park-tbilisi' and 'listing:new-projects-in-avlabari'), which adds real meaning about expected format. It still does not enumerate the allowed prefixes or explain what qualifies as a valid source.

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 gives a specific verb+resource: 'Add a source to the weekly sweep.' Combined with the sibling 'untrack', an agent can infer this is the inverse registration operation. It does not explicitly name untrack/list_tracked as alternatives, so it falls short of full sibling differentiation.

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?

Usage is implied by 'add a source to the weekly sweep' — the agent can infer this is for registering something to be monitored. However, there is no explicit when-to-use guidance, no mention of the untrack inverse, and no statement about preconditions such as whether the source must already exist.

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