PearlGraph

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context such as "near = attraction id within 90 min drive," "permit capacity per sector and access rules," and "low season permit rates for April, May and November," though it does not discuss auth, limits, or error behavior.

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 dense but appropriately sized for a 13-action dispatcher and is front-loaded with the tool's purpose. The semicolon-separated action list makes it scannable, though the single long paragraph is somewhat run-on and could be more clearly structured for an agent parsing many actions.

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 complex multi-action tool with an output schema and safe read-only annotations, the description covers all actions and the main parameter semantics. It does not explicitly state which parameters are required per action, which is a meaningful gap given that the schema itself only requires `action`, but the action parameter lists provide enough implied guidance for most calls.

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 0%, so the description carries the full burden and does a strong job mapping parameters to actions, e.g. "route (from, to, month)," "lodges (near, tier, district, type, query)," and "graph (query = id or name, depth 1-2, predicate)." It also defines nontrivial semantics like `near` as an attraction id within 90 minutes and lists valid graph predicates. It does not fully explain nested `stops`/`days` object shapes or action-specific requiredness, so it is not complete enough for a 5.

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 opens with a precise scope statement: "Single entry point to all PearlGraph Uganda tourism data," then enumerates all 13 supported actions and their domains. An agent can immediately tell this is a multi-action Uganda tourism dispatcher rather than a single-purpose tool.

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 explicitly says "Pick an action" and then gives action-level usage context for every option, including examples such as search "meaning-based search over free text, e.g. 'see apes in rainforest'" and graph predicates. It also states the key prerequisite that "Ids come from earlier results (e.g. kampala, bwindi-rushaga)," which is essential for correct invocation.

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