Save To Shortlist

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

Discloses persistence across conversations, API-key scoping, creation of the list if new, snapshotting of objectives and current percentile score, default equal weighting when objectives are omitted, and reuse of ranked metrics. The mutation side effect is clearly stated, the API-key dependency is surfaced, and there is no contradiction with the annotations.

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 longer than average but every sentence is information-dense, front-loading the core purpose and persistence guarantee before usage and parameter guidance. The minimal call example and conditional ranking instructions earn their place, with no 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 4-parameter stateful mutation with only basic annotations, the description covers the minimal and rich call forms, optional parameters, behavior over time, API-key requirement, and complementary next step. The output schema fills return-value details, so nothing essential is missing for an agent to invoke it correctly.

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%, yet the description still adds meaning: it identifies the MINIMAL site object shape, explains that richer metric fields get reused in re-scoring, clarifies that objectives are optional with a default equal-weighting behavior, and notes that shortlist_name is created if new. This is substantial added value 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?

States a specific verb and resource: 'Save a site into a PERSISTENT, named shortlist that survives across conversations.' It distinguishes the tool from read/complementary siblings by emphasizing persistence, API-key scoping, and Phase 5 statefulness, and it specifically names get_shortlist as its pair, so an agent can tell what this tool is for.

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 says 'Use to build a durable siting shortlist across days/weeks' and says to pair with get_shortlist for re-scoring, giving clear context. It also provides a prerequisite and example call shape ('call claim_free_key first'). It does not explicitly state when not to use it versus the similar save_site sibling, so it misses the when-not exclusion.

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