BrainDrops

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

The annotations confirm this is a safe, read-only operation. The description adds critical contextual behavior by listing the specific, complex technologies involved in the preservation (e.g., Arweave, IPFS pinning), giving the agent a deeper understanding of the underlying 'data state' beyond the safety hints.

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, perfectly structured sentence that addresses the core function and the necessary verification step without any filler. It is highly efficient.

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 its informational, static nature and zero parameters, the definition is entirely complete. The description covers the 'what' (preservation methods) and the 'how' (verification), and the annotations cover the safety profile.

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?

With zero parameters and 100% schema coverage, the description cannot add specific parameter semantics. This score represents the baseline expectation for tools with no complex inputs.

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 is highly specific, outlining not just that it provides information, but exactly *what* information it provides: the various archival mechanisms (Ethereum, Arweave, IPFS) and the method for verification. This distinguishes it from simple data retrieval siblings like get_piece.

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?

Since this is a 0-parameter, information-providing tool, its usage is defined by necessity—when the agent needs to know the preservation policy, which is outside the scope of data retrieval tools like get_collection. It clearly targets conceptual queries rather than data lookup.

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 and openWorldHint=false, so the safety profile is covered. The description contributes the returned field set (artist, size, release date, facts, token range, links), which matters because there is no output schema, but it says nothing about resolution behavior — whether name, slug, or project ID all work identically, or what happens on a miss.

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 front-loaded sentence with zero filler; every element is either the verb, the scoping ('one'), or a returned field. The field list is dense but each item earns its place given no output schema.

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 tool with full schema coverage and annotations covering safety, the only real gap the description must fill is the return shape — and it does. Missing only failure-mode and identifier-resolution notes, which are minor for this complexity.

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 single parameter is fully documented in the schema ('Collection name, slug or project ID'), so coverage is 100%. The description adds nothing about identifier formats, case sensitivity, or ambiguity between a name and a slug, so 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?

A specific verb plus resource ('Get one BrainDrops collection') with an enumerated field list, so the agent knows exactly what comes back. The singular 'one' implicitly contrasts with list_collections, but no sibling is named 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?

No when-to-use guidance, no prerequisites, and no alternatives named. With list_collections and search_braindrops as siblings, the description never states that the collection identifier should be discovered via list_collections or search first.

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 cover read-only and closed-world behavior, so the description's added value is in disclosing the return payload, including the four 'permanent copies' (Ethereum token, Arweave metadata, Arweave HD image, IPFS original) — useful context given no output schema exists. It does not mention failure behavior when neither identifier resolves to a piece.

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, zero filler. The resource and returned fields come first, and the invocation rule is front-loaded in a short trailing clause.

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?

With no output schema, the description does the necessary work of listing the returned fields so the agent knows what a call yields. It is nearly complete for a simple lookup; only the behavior on a non-matching or ambiguous identifier is unaddressed.

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 baseline is 3, but the description adds meaning the schema never states: that token_id and collection+number are two alternative lookup paths rather than parameters to combine. That resolves the ambiguity of three all-optional parameters sharing one lookup.

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?

It states a specific verb and resource ('Get one BrainDrops piece') and enumerates exactly what the record contains (name, artist, collection, traits, images, permanent copies), which implicitly separates it from the collection-level and search siblings. It never names an alternative tool explicitly, so sibling differentiation is left 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 final clause 'Give token_id, or collection + number' tells the agent how to invoke it with two alternative key sets, which is real usage guidance. It stops short of saying when this tool is preferable to get_collection or search_braindrops, and gives no 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?

While annotations cover safety (readOnlyHint: true), the description provides specific behavioral context by listing the metadata returned (artist, size, release date). This helps the agent anticipate the utility and content of the resulting list.

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 sentence is extremely concise, directly stating the action and the scope of the data provided without any extraneous language.

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 that the tool accepts 0 parameters, the description fully communicates what the tool achieves and the quality/type of data it returns, making it contextually complete for the agent.

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?

Since there are 0 parameters, the baseline is high. The description adds value by defining the fields that will be contained within the collection list (artist, size, release date), which is helpful without an output 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 uses a specific verb ('List') and clearly identifies the resource ('BrainDrops collection'). By listing 'every' collection, it defines its scope and distinguishes itself from specific retrieval functions like get_collection or search_braindrops.

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 defines the tool's function as a complete enumeration of resources. Compared to sibling tools that suggest specific filtering or detail fetching, this tool is clearly identified as the high-level comprehensive list function.

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 and openWorldHint=false, so the safety profile is covered; the description adds that results include both collections and pieces plus links, which the agent cannot learn from structured data. It omits ranking/ordering behavior and any note that matches may be partial, keeping it below 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?

Two tight sentences: the capability and searchable fields come first, then what is returned. The inline query examples do real work and nothing is redundant.

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?

With no output schema, the description correctly summarizes the return shape (matching collections and pieces with links). For a small two-parameter read-only tool this is nearly sufficient; only result ordering/pagination and the meaning of 'limit' are left unstated.

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%: 'query' is documented only as 'What to look for', and the description meaningfully compensates by explaining the searchable fields and the 'collection number' syntax (e.g. 'loops 42'). The 'limit' parameter gets no treatment in either schema description or prose, so the coverage gap is only partly closed.

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?

Names a specific verb and resource (search BrainDrops collections and pieces) and enumerates the searchable fields, so an agent can tell it apart from direct-lookup siblings like get_piece or get_collection. It stops short of explicitly contrasting with those siblings, but the 'search' framing is unambiguous.

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 listed searchable fields and the example query forms, which hints at when this tool fits. However, it never says when to prefer this over get_piece/get_collection or what to do when a search returns nothing, so guidance remains inferred rather than stated.

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