get_sources

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It conveys this is a read-only retrieval of cached sources, which is inherently safe, and hints that data persists ('cached'). It does not mention what happens for invalid/expired session_ids, auth requirements, or pagination, but for a simple retrieval tool the basic safety profile is adequately conveyed.

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 highly repetitive — three sentences effectively say the same thing: use the web_search session_id to get the source list. It also contains a typo ('invoke the this tool'). A single crisp sentence ('Retrieve all cached sources for a prior web_search call using its session_id.') would carry the full meaning. The redundant first sentence should be cut.

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?

An output schema exists, so the return format is covered externally. For a low-complexity tool with a single required parameter, the description adequately covers when to use it (after web_search) and what it returns (the full source list). The main gaps — error behavior for invalid sessions and any filtering/ordering — are minor given the tool's simplicity.

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% — the schema already documents session_id as 'Session ID from previous web_search call.' The description reinforces that the ID must come from web_search, adding marginal provenance context, but it does not add meaningful syntax or format details beyond what the schema provides. Baseline 3 is appropriate.

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 core purpose is clear: 'Retrieve all cached sources for a previous web_search call' states a specific verb and resource, and ties the tool to the web_search sibling via session_id. However, the opening sentence uses odd emotional framing ('When you feel confused or curious...') which muddies the definition rather than clarifying it. The purpose is distinguishable from siblings like web_fetch and web_map because it targets cached search sources.

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 useful context: the tool is invoked with a session_id returned by a prior web_search call, so it is clearly a follow-up to web_search. However, it never states when NOT to use it or names alternatives (e.g., web_fetch for fetching actual page content). The 'confused or curious' trigger is too vague to be actionable guidance.

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