WeAD

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

With no annotations, the description carries the full burden of behavioral disclosure. It signals a read operation and that only 'open' documents are targeted, but it does not explain what 'open' means, what is returned, error behavior, or permission requirements.

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 front-loaded sentence with no wasted words. The core action and key constraint are immediately clear.

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 one-parameter read tool, the description is adequate for invocation and identifies the name source. However, with no output schema and no annotations, it leaves return values, error handling, and the meaning of 'open' unspecified.

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 0% and the only parameter is undocumented in the schema. The description adds useful meaning by indicating that 'name' is a document name sourced from list_documents, but it does not specify format, case sensitivity, or exact-match behavior.

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 (Read) and resource (one open WeAD document) with the retrieval key (by name). It clearly distinguishes this from list_documents by emphasizing singular retrieval and even references list_documents as the source of valid names.

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 'as returned by list_documents' gives clear context for when to use this tool: after obtaining a document name from listing. It does not explicitly exclude search_documents or specify edge cases, so it falls short of full when/when-not guidance.

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?

With no annotations, the description must carry the behavioral load; it does signal authority ('truth surface', read-before-claiming), implying the result should be trusted as canonical. It does not confirm read-only semantics, describe the shape or size of the response, or explain what 'early' and 'roadmap' values mean in practice.

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 short sentences, front-loaded with the tool's role, with no repetition or filler. The only cost is that the leading phrase is jargon rather than plain description.

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 zero-parameter read with no output schema and no annotations, the description should say roughly what comes back (a list of features with status labels? a status object?). It establishes trust and timing but leaves the response shape entirely to discovery, which is a real gap given nothing else documents it.

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 takes zero parameters and the schema is an empty object, so there is nothing parameter-level the description needs to compensate for. Baseline 4 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 conveys the returned content ('what is actually live versus early or roadmap'), which distinguishes it from the document-oriented siblings, but the metaphorical framing 'truth surface' never states plainly what the resource is (features? capabilities? product areas?) or supplies a verb like 'returns'. An agent can infer it's a capability-availability read, but only by interpreting jargon.

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?

'Read this before making claims about WeAD' is an explicit, actionable when-to-use directive that tells the agent to consult this tool prior to asserting anything about the product. It stops short of naming alternatives or when-not-to-use conditions, but the positive trigger is unambiguous.

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?

With no annotations, the description carries the full behavioral burden. It implies a read-only listing and mentions returned fields, but does not disclose pagination, ordering, authentication needs, rate limits, or whether 'every' app is truly exhaustive.

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 efficient sentence with the resource and returned fields front-loaded. There is no redundant or filler content.

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 list tool with one optional filter and no output schema, the description covers the resource, filter values, and key return fields. However, it omits pagination, ordering, and other behavioral details that would fully prepare an agent without annotations.

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%, and the single optional 'stage' parameter is fully documented in the schema. The description repeats the allowed stage values but adds no additional filter semantics beyond what the schema already provides.

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 ('List') and resource ('every WeAD app'), plus the returned fields ('stage' and 'link'). It does not explicitly differentiate itself from siblings, but the resource is clearly distinct from documents/status 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?

Usage is only implied by the verb 'List'; there is no guidance on when to use this tool versus alternatives. No exclusions, prerequisites, or routing hints are provided.

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?

With no annotations, the description carries the full burden. It conveys only that the listing is scoped to 'open' documents; it says nothing about ordering, pagination, whether closed documents are excluded entirely, permissions needed, or what an empty result means. For a zero-annotation tool this is a thin behavioral contract.

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?

One compact sentence with the scope qualifier ('open') and the returned content front-loaded. No filler, though the parenthetical list is longer than strictly needed.

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?

A zero-param list tool with no output schema needs little, and the description names the documents returned. It stops short of covering result shape or ordering, which an agent would have to discover by calling it.

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 takes no parameters, so there is nothing for the description to disambiguate. Baseline 4 applies, and the sentence does not muddy things with phantom 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?

States a specific verb (List) and resource (WeAD research documents) and enumerates the document types it returns, so an agent knows exactly what comes back. It does not explicitly contrast itself with search_documents or get_document, leaving sibling differentiation to inference.

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 word 'open' implies this is the unfiltered enumeration path, but nothing states when to prefer it over search_documents or get_document. Usage is implied rather than directed.

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?

With no annotations, the description carries the full disclosure burden. It does add real context by scoping results to "open" documents and stating the return shape ("matching passages"), but says nothing about result limits, ranking, or whether closed documents are silently excluded.

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 front-loaded sentence with zero filler: verb, scope, input type, and return shape all in one clause chain. Nothing to trim.

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 search tool with no output schema, the description covers what an agent needs to call it and roughly what comes back (matching passages). Pagination and result-count behavior are the only meaningful omissions.

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 0% and the single parameter has no description, but the tool description compensates by defining the query as a "word or phrase" rather than an id, which is the key semantic distinction for a search input. It stops short of stating matching behavior (substring vs. full-text token matching).

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 pairs a specific verb ("Search") with a specific resource ("open WeAD documents") and states the input type (a word or phrase). That clearly separates it from get_document (fetch by id) and list_documents (enumerate), though it never names those siblings explicitly.

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: reach for this when you have a word or phrase to locate rather than an identifier. The description gives no explicit when-not guidance and does not steer the agent toward get_document or list_documents, leaving the choice to inference.

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