Cerebrium Docs

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

Beyond the annotations, the description discloses critical behavioral traits: the filesystem is a sandbox not a real machine, no writes/network/process control are allowed, each call is stateless with working directory reset, and output is truncated to 30KB per call. It also explains the supported commands and path-to-URL conversion. This substantially exceeds what the annotations alone provide.

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 long but every section earns its place: safety clarification, workflow, command list, statelessness warning, concrete examples, truncation guidance, and URL conversion. It is well-structured with headers and examples, and the most critical scoping information is front-loaded in the first sentence.

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 tool with no output schema, the description is remarkably complete. It covers what the filesystem contains, what commands work, how to explore and read pages, statelessness implications, output limits, and how to reference pages in responses. An agent has everything needed to invoke the tool correctly and interpret results.

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?

Although the schema covers the single `command` parameter at 100%, the description adds extensive practical meaning: supported commands, examples, chaining with `&&`, absolute paths, truncation behavior, and reading multiple files in one call. This goes far beyond the schema's one-line parameter description.

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 and resource: "Run a read-only shell-like query against a virtualized, in-memory filesystem rooted at `/`" containing only Cerebrium documentation and OpenAPI specs. It clearly distinguishes itself from the sibling search_cerebrium by explaining the tool is for exact keyword/regex matching, structural exploration, and reading specific pages by path, rather than broad conceptual search.

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 explicit workflow guidance: "Start with the search tool for broad or conceptual queries" and "Use this tool when you need exact keyword/regex matching, structural exploration, or to read the full content of a specific page by path." It also specifies how to chain commands in one call and warns about statelessness, leaving little ambiguity about when and how to use it.

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, idempotent, and non-destructive behavior. The description adds useful behavioral context by explaining that search returns contextual content with titles and direct links, and that it does not return full page content, steering the agent to the sibling tool when needed.

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 compact and front-loaded: the first sentence states the core purpose, the second gives usage guidance, and the third provides a concrete handoff to the sibling tool. The .mdx example is useful and 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?

Given the simple two-parameter schema and existing annotations, the description is complete enough for an agent to select and invoke the tool correctly. It compensates for the lack of an output schema by describing the return format and by explaining how to get full documentation content elsewhere.

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 input schema already documents both parameters fully with 100% coverage, so the description does not need to repeat parameter details. The description adds no significant parameter-level meaning beyond the schema, which is acceptable given the high 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 identifies a search operation over the Cerebrium knowledge base, lists the kinds of information it finds, and distinguishes it from the docs-filesystem sibling. The verb and resource are specific, so an agent can understand what the tool does without opening the schema.

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 explicit when-to-use conditions such as answering questions, finding documentation, understanding features, and locating implementation details. It also gives a clear alternative for full page content, naming query_docs_filesystem_cerebrium and providing a concrete example with the .mdx path convention.

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 describe a non-read-only, non-idempotent, non-destructive operation, and the description adds helpful real-world context: feedback is submitted to the docs team so they can fix the issue. This goes beyond the structured annotations without contradicting them. It leaves out details like confirmation behavior or persistence, but with annotations present this is a reasonable level of disclosure.

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: the action and intended effect, the concrete use cases, and the exclusions. It is front-loaded with the core purpose and contains no redundant or filler 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?

For a simple two-required-parameter feedback tool with no enums or nested objects, the description is complete. It explains the tool's purpose, when to use it, what not to use it for, and the response-like outcome ('docs team can fix it'), so an agent has enough context to select and invoke it correctly.

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 both 'path' and 'feedback' already well documented, including an example path and guidance on what kind of feedback to provide. The description adds no additional parameter semantics, so the baseline score of 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 names a specific verb and resource: 'Report a problem with this documentation site' for the docs team. It also clearly separates this tool from search/query siblings by framing it as feedback about documentation content, not product support or feedback about the tool/assistant. This makes the tool's purpose 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?

The description explicitly lists when to use it: when a documentation page is incorrect, outdated, confusing, incomplete, or has a broken example. It also gives clear exclusions, such as product support requests and feedback about the tool/assistant. However, it does not name the sibling query/search tools as the alternative, so an agent must infer the routing from the sibling names.

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