Amito — Interface specifications

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

Annotations already declare read-only, idempotent, closed-world, and non-destructive behavior. The description adds useful context beyond annotations by stating what is returned and explicitly ruling out arbitrary URL/file fetching, though it does not describe error behavior for invalid IDs.

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 three tight sentences with the core purpose front-loaded. Each sentence adds useful information: ID provenance, return contents, and scope limitation.

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 rich annotations and an output schema, the description covers the essential context: where the ID comes from, what the tool returns, and what it does not do. Nothing critical is missing for correct invocation.

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%, so the description must carry parameter meaning. It does so by defining the id as an exact document ID returned by search, giving concrete examples such as spec:form and project:dupe, and clarifying that URLs are not accepted.

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 gives a specific verb and resource: reading a document by exact ID. It clearly distinguishes this from search by saying the ID is returned by search, and from URL fetching by explicitly excluding arbitrary URLs/files.

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 states the required workflow condition: use an exact document ID returned by search. It also states a clear exclusion: does not fetch arbitrary URLs or files, which prevents misuse as a general URL fetcher.

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 readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new behavioral context: results are pointers (document IDs plus source URLs) rather than full documents, which tells the agent to expect to chain into fetch. It doesn't disclose ranking, result limits, or query matching 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?

Two sentences, zero waste. The primary purpose is front-loaded and the fetch hand-off is a compact trailing clause. Nothing could be removed without losing signal.

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 only one parameter and an output schema present, the description covers what an agent needs to select and call the tool: corpus scope, return shape, and the follow-up tool. The remaining gap is query formulation guidance, which matters given the zero-coverage parameter.

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 'query' parameter has 0% schema description coverage, so the description must carry the burden, and it only implies free-text search without stating whether it accepts keywords, phrases, or natural-language questions. The 300-character cap and the dual corpus (specs vs. project facts) make query strategy non-obvious, and that gap is unaddressed.

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 names a specific verb ('Find') and enumerates the resource types covered — forms, tables, onboarding, dashboards, and public facts about specific projects — and names what the tool returns (document IDs and source URLs). An agent can immediately tell this is a discovery tool over a bounded corpus rather than a content-retrieval 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 routes the agent to the 'fetch' sibling for complete content, which is the key when-to-use pivot for a search tool. It does not mention the other sibling, validate_design_spec, or state when not to search, so it stops short of full alternative coverage.

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 readOnly, idempotent, non-destructive and closed-world, so safety is covered structurally. The description adds genuine behavior context — it returns missing or placeholder decisions plus acceptance scenarios, and it does not persist the draft — but with no output schema it could say more about the shape and size of that result.

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?

Four short sentences that are front-loaded with purpose, then prerequisite, then the semantics of the `decisions` payload, then return content and exclusions. No sentence is redundant with the others.

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 two-parameter read-only validator with no output schema, the definition covers purpose, prerequisite, payload semantics, return content, and exclusions. It leaves vague what qualifies as a "placeholder" decision and how large a result set can be returned.

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%, so the description must carry parameter meaning, and it does: `pattern` selects which decision set applies, and `decisions` keys must come from the fetched spec while each value describes intended behavior with a rationale when a requirement does not apply. It omits any note on the key/value length limits that the schema enforces.

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 and object ("Check whether a draft supplies the required decisions") and bounds it to four named pattern families. It also implicitly distinguishes itself from the fetch sibling by noting that spec:<pattern> must be fetched first for the exact decision keys.

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?

Gives a concrete prerequisite workflow ("First fetch spec:<pattern>") and explicit scope exclusions ("Does not inspect code, certify accessibility, or save the submitted draft"), so the agent knows what not to expect. It stops short of naming a sibling alternative for the non-validation cases, but the routing intent is clear.

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