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

With no annotations at all, the description carries the full burden of behavioral disclosure, and it only covers the output shape (endpoints, sources, 'why'). It does not disclose how ambiguous intents are handled, whether the tool performs live lookups or returns cached mappings, latency/cost implications, or failure modes. For a router that brokers access to other endpoints, this is a substantial gap.

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?

A single sentence with no filler; the core mechanism, target resource, and return value are all present. Slight deductions for the ambiguous terms 'knowledge' and 'why' (quoted but undefined) and for the semicolon structure mixing imperative with outcome phrasing.

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?

This is a complex routing tool with no output schema and no annotations, so the description must explain return behavior and result semantics. It does not describe the structure of returned endpoints, how many can be returned, the format of the 'why', or behavior for unknown intents. An agent would have to call the tool blindly to learn these.

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 must compensate, but it only glosses over the intent parameter ('Describe what you need in natural language') and says nothing about 'limit' — its range, meaning, or whether it caps endpoints, sources, or both. With two parameters at zero schema coverage, this is insufficient.

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 identifies a concrete function: taking a natural-language knowledge need and returning the fitting HeatPulse endpoint(s) plus external sources with a rationale. It clearly differentiates this from direct-access siblings like search_news or list_datasets by positioning it as a routing/discovery layer. It loses a point because the verb phrase is informal ('Describe... get back') and it doesn't explicitly name which sibling it replaces or complements.

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: an agent would call this when it knows what knowledge it wants but not which HeatPulse endpoint fits. However, there is no explicit when-to-use statement, no 'use instead of X when...' routing condition, and no mention of when to prefer direct siblings like search_news. The guidance is inferable but not stated.

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