DaedalMap Hurricane and Tropical Cyclone Data

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

Annotations already declare readOnlyHint=true, and the description adds 'Free discovery' to convey that no cost or auth is needed. It does not detail return format or error behavior, but for a parameterless read-only operation, the provided context is adequate.

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 two concise sentences: 'Free discovery. Returns the list of live agent-ready data packs available on DaedalMap.' Every phrase adds value, with the purpose front-loaded and no fluff.

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 parameterless read-only tool, the description sufficiently explains what it returns and adds platform context. It does not elaborate on the structure of 'data packs' or output format, but given the lack of an output schema and the tool's simplicity, the description is nearly complete.

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?

The tool has zero parameters, and the schema covers 100% of parameters vacuously. Per the rubric, a baseline of 4 is appropriate when there are no parameters, and the description adds no unnecessary detail about parameters.

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 clearly states the tool's function: 'Returns the list of live agent-ready data packs available on DaedalMap.' This specifies the verb (Returns), the resource (list of data packs), and the platform, distinguishing it from siblings like get_pack and query_dataset.

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 phrase 'Free discovery' and the description of returning the catalog make it clear this is the tool for listing available data packs, not for querying or searching. However, it does not explicitly mention alternatives or exclusions, so it stops short of a full 5.

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 readOnlyHint=true, so the safety profile is covered. The description adds 'Free discovery' and output content context, but it does not disclose additional behavioral traits such as rate limits, response structure, or potential side effects. This is adequate but not rich.

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?

Two sentences with no filler. The core action and output contents are front-loaded, the usage timing is stated clearly, and every clause earns its place.

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 simple read-only lookup with one required parameter, the description covers what is returned, when to call it, and where the pack_id comes from. It is slightly vague about how the returned 'canonical tool guidance' should be used, but nothing critical for invoking the tool is missing.

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 100%, so the schema already documents pack_id as a pack identifier from get_catalog. The description reinforces that the tool operates on 'one pack' but adds no meaningful parameter semantics beyond the schema. Baseline 3 applies.

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 uses a specific verb ('Returns') and clearly identifies the resource ('one pack') along with the kind of information provided ('metadata, coverage, freshness, preferred canonical tool guidance, and first-query examples'). It does not explicitly differentiate from sibling tools like get_catalog, but the 'one pack' framing makes the per-pack lookup intent clear.

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 an explicit usage directive: 'Call this before querying a new pack.' This tells the agent when to invoke the tool and why. It does not mention exclusions or alternatives, so it falls short of a full 5.

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 declare readOnlyHint=true, so safety is known. The description augments this by detailing the return payload and the interaction contract. It doesn't describe failure behavior on invalid tool_name, but that's not critical for a read-only help tool.

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?

Two sentences, front-loaded with purpose, packed with useful detail without padding. Every sentence earns its place.

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 one-parameter read-only helper, the description tells what to expect in the response and how to use it. It lists the response contents, so no output schema is needed.

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 covers tool_name 100% with a clear description ('Exact tool name from tools/list'). The description adds usage context (call before unfamiliar tool) but no additional syntax requirements, so 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 description clearly states the tool returns guidance for any visible tool, listing specific content types (when to use, refusals, example, limits, outputs, provenance, next calls, interaction contract). This distinguishes it from sibling data tools (get_catalog, search_disaster_links) as a meta-help 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?

Explicitly instructs to call tools/list first, then call this before unfamiliar tool. This gives a clear when-to-use policy and a workflow. Sibling tools are for data, so no confusion about alternatives.

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 declare readOnlyHint=true, so the safety profile is already known; the description adds useful context by disclosing that paid packs incur x402 Base USDC costs, which is genuinely actionable behavioral information. Still, it does not describe response format, error conditions, or what happens when neither source_id nor pack_id is supplied, so the burden beyond annotations is only partially met.

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?

Two sentences with the purpose front-loaded ahead of the pack list; no wasted words. The lengthy but functional enumeration of free vs. paid packs earns its place because it encodes availability and cost distinctions the agent needs, keeping the overall structure tight.

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 an 8-parameter tool with nested objects (filters with time/region_ids/compare clauses) and no output schema, the description should cover return format and effective requirements, but it does neither. It leaves implicit that at least one of source_id or pack_id is needed (all params are optional) and does not disclose response shape, so an agent is left with gaps despite strong schema coverage.

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%, so the schema already documents all 8 parameters with meaningful descriptions (source_id examples, pack_id pointing to get_catalog, limit maximum/minimum). The description adds the API-contract pointer but no parameter-level detail beyond the schema, so the 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 description opens with a specific verb+resource: 'Generic structured query for direct source_id or pack_id access', which precisely states what the tool does and how it is invoked. It also names the API contract (POST /api/v1/query/dataset) and the pack taxonomy, clearly distinguishing it from siblings like get_catalog (listing) and get_pack (pack retrieval).

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 implies the tool is for direct source_id or pack_id data access and enumerates the available free and paid packs, which helps an agent know when the tool is usable. However, it never explicitly states when NOT to use it or names alternatives (e.g., 'use get_catalog to discover pack_id first'), leaving routing between siblings to inference.

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?

The readOnlyHint annotation already communicates that this is a safe read operation, so the description only needs to add extra context. It adds the discovery-oriented behavior ('discover whether a relationship family exists') but doesn't disclose pagination, result ordering, or limitations. This matches the expected baseline when annotations cover safety.

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 only two sentences, with the purpose front-loaded in the first sentence and the use case in the second. Every word earns its place, and there is no redundancy or 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?

Given the tool's moderate complexity (7 optional parameters, no output schema), the description sufficiently explains the discovery scenario and the available filtering dimensions. It does not describe the return value shape, but for a search/discovery helper, the purpose and use case are clearly communicated, leaving only minor gaps.

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 100%, with each parameter (limit, year_start, year_end, event types) well-documented. The description's mention of 'event-type direction' and 'year window' aligns with the schema but doesn't add new semantic meaning beyond what the parameter descriptions already provide. 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 description clearly states the tool's function: 'Searches published cross-disaster link families by event-type direction, optional via-event type, and optional year window.' It uses a specific verb ('searches') and resource ('link families'), and the context of discovery ('before you have an exact event id') distinguishes it from sibling tools like get_catalog.

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 provides clear guidance on when to use: 'Use this when you want to discover whether a relationship family exists before you have an exact event id.' However, it does not explicitly state when not to use it or mention alternative tools, so it stops short of a full when/when-not/alternatives breakdown.

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