docbin

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

The description discloses important runtime behaviors beyond the annotations: that re-using a name creates a new immutable version, that omitting the name yields a random one, and that inlining large content streams through the model and times out. Annotations only declare readOnlyHint=false and destructiveHint=false, so these additions materially help an agent predict side effects and failure modes.

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 longer than average, but each sentence contributes: purpose, versioning behavior, random-name behavior, size threshold, shell alternative, why (timeout). It is front-loaded with the core action and uses no fluff, though it could be slightly tighter by trimming the inline example.

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?

The tool has an output schema, so return-value documentation is not required in the description. The description covers the essential operational constraints (size limits, alternatives, auth token for the fallback command) and the schema covers parameters and cross-file linking rules. Nothing needed for correct invocation 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 coverage is 100%, so the baseline is 3; the description adds extra meaning on top by explaining name-versioning semantics and the ~10KB practical limit for inline content, which the schema does not convey. It doesn't repeat every parameter, but the schema already covers files, content_type, visibility, and language in detail, so the incremental description value justifies a 4.

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 first sentence states a specific verb and resource: 'Create a document and return its public URL.' It also describes key behavioral facets (versioning on name reuse, random name generation), which makes the tool's function unmistakable against siblings get_doc and search_docs.

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 explicitly tells the agent when NOT to use this tool ('content larger than ~10KB or any file already on disk, do NOT inline it here') and names a concrete alternative ('run `docbin push <file>` in your shell instead'), including the required DOCBIN_TOKEN setup. This is stronger than the typical 'use when...' guidance; it gives an exclusion plus a fallback.

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?

readOnlyHint=true already signals a safe read, and the description adds useful default behavior (own handle, latest version). It does not disclose failure modes, permission requirements, or return format specifics, though the output schema covers the latter. The added context is moderate but not extensive.

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. The primary action and resource are front-loaded, and the default behavior is stated in a separate sentence. No filler or redundant framing exists.

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 retrieval tool with an output schema and readOnlyHint annotation, the description covers the essential behavior and defaults. It could add explicit guidance distinguishing it from search_docs, but nothing critical for invoking this tool correctly 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 all three parameters are already documented. The description's mention of defaults ('Defaults to your own handle and the latest version') essentially repeats the schema descriptions, adding no new semantic information beyond what the schema 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 uses a specific verb ('Fetch') and resource ('raw stored content of a document'), making it clear this retrieves document content. It distinguishes itself from sibling tools create_doc and search_docs by focusing on raw content retrieval rather than creation or searching.

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: the tool fetches raw content, so it contrasts with searching or creating, but there is no explicit guidance on when to choose this over search_docs or whether it handles metadata lookups. No alternatives or exclusions are named.

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 annotations already declare readOnlyHint=true, so the agent knows this is safe and non-mutating. The description adds useful behavioral context about the return payload (URLs and latest versions) beyond what annotations provide. No contradictions with annotations.

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, with the core action stated first and no filler. Every clause adds information—search scope and return contents. This is an appropriately concise definition.

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 single-parameter read-only search tool with an output schema present, the description covers the essential behavior and result contents. It doesn't detail match semantics (e.g., substring vs exact, case sensitivity), but those are not critical for a correct call. The tool is simple enough that this description is complete for an 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?

The schema already fully documents the only parameter 'q' with 'Search query matched against doc names.' The description reinforces this with 'Search your documents by name' but doesn't add meaningful semantic detail beyond the schema. Baseline 3 is appropriate given 100% schema coverage.

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 a specific verb ('Search') and resource ('your documents') and narrows the search to 'by name.' It also mentions the return content (URLs and latest versions), which distinguishes it from the sibling tools create_doc and get_doc.

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 provides clear context: use this tool when searching for documents by name. It doesn't explicitly name alternatives or exclusions, but the sibling names (create_doc, get_doc) make the use case obvious. It lacks the explicit when-not-to-use guidance needed for a 5.

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