Common Ground

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. Beyond that, the description adds meaningful context: it uses Qloo's taste graph to score candidates and returns the option that maximizes the least happy person's happiness, with a reason per person. That reveals the selection logic and return content, though it does not discuss failure modes or rate limits.

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 a single dense paragraph but is front-loaded with the core action and packs almost every sentence with useful information. It is appropriately sized for the tool's complexity, though the run-on structure could be easier to scan.

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?

Given four parameters, low schema coverage, no output schema, and no sibling tools, the description covers the essential inputs, the taste-transfer mechanism, the scoring objective, and the return shape (a pick plus per-person reasons). It omits minor constraints such as the maximum group size, but an agent can call it correctly from this definition.

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 description coverage is only 25%, so the description must compensate, which it does: it explains the `kind` categories, the 2–5 `likes` per member, the `location` requirement for places, and the purpose of `tasteFrom` with concrete examples including `any`. It leaves some constraints like the maximum of 8 members to the schema, but adds substantial meaning over the raw 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 states a specific verb and resource: it picks ONE movie, TV show, book, artist, podcast, restaurant, or destination for a group. It also names the underlying mechanism, Qloo's taste graph, and the optimization goal, making the tool's function unambiguous even without sibling tools.

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?

It clearly explains how to use the tool: provide each person's name and 2–5 likes, use `tasteFrom` when favorites come from another category, and include `location` when `kind=place`. It does not include explicit exclusions or 'when not to use' guidance, but there are no sibling alternatives and the usage context is clear.

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

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

Annotations already declare the tool read-only, idempotent and non-destructive, so safety is covered. The description adds genuinely new behavioral context: the maximin selection rule ('each stop is the venue whose least happy friend is happiest') and that Qloo explainability returns the favourite items and each friend's taste share. It doesn't discuss failure modes or rate limits, which keeps it from a 5.

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?

Four sentences, front-loaded with the task and followed by input expectations and the ranking/explainability behavior. Every sentence carries signal. The final sentence is dense but still informative rather than padded.

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?

There is no output schema, so the description has to describe the return value, and it does: a sequence of stops with the chosen venue and the explainability breakdown. Combined with the input expectations, an agent has enough to call it correctly. The only gap is the lack of guidance on the sibling tool.

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 50%: city and members[].likes have schema descriptions, while members[].name and the members array do not. The description partially compensates by explaining that each friend needs a name plus 1-4 liked artists, movies, shows or books, and that these can be mixed freely. That mostly restates the schema rather than adding syntax or format guidance.

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 states a specific verb and resource: it builds an evening itinerary of dinner, drinks and live music in one city for 2-6 friends. An agent can immediately tell what the tool produces. It stops short of distinguishing itself from the sibling find_common_ground, so it is clear but not fully differentiated.

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 the scenario ('Plan dinner, drinks and a live music venue… for 2 to 6 friends'), and input expectations are restated. However, the description never says when to choose this over find_common_ground, and gives no exclusions or preconditions beyond the member count.

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