Cerebrium Docs

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description adds substantial context beyond that: the sandbox is virtualized and in-memory, no writes/network/process control, calls are STATELESS with working directory resetting to `/`, and output is truncated to 30KB per call. The statelessness and truncation warnings are the kind of behavioral detail annotations cannot convey. Minor gap: no coverage of latency or command-failure semantics, keeping it from 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?

Front-loaded with the core purpose and bold-sectioned (Workflow, Supported commands, statelessness, examples), so it scans well. It is longer than strictly necessary — the OpenAPI mounting details and multi-example list add bulk — but nearly every section earns its place for a complex tool.

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?

Despite no output schema, the description explains output characteristics (truncation limit, md-to-URL path conversion), command capabilities and limits, and the stateless execution model. For a single-param tool this is more than complete enough to invoke and interpret results 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 coverage is 100% for the single `command` param, so the schema carries baseline weight. The description nonetheless enriches semantics considerably with supported-command lists, `--help` guidance, and multiple concrete command examples, though these are scattered rather than mapped per-parameter.

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+resource ('run a read-only shell-like query against a virtualized, in-memory filesystem') and immediately scopes it to Cerebrium docs pages and OpenAPI specs. It also explicitly distinguishes itself from the sibling search tool and clarifies there is no separate get-page tool, so an agent can place it among siblings without opening schemas.

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 explicit routing: use the search tool for broad/conceptual queries, use this tool for exact keyword/regex, structural exploration, or reading a page by path. It even specifies a discovery workflow (tree/ls before reading) and the alternative when a path guess fails (rg -il). This is textbook when/when-not/alternatives 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?

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description still adds value beyond them by disclosing the return shape (contextual content with titles and direct links) and the downstream path-mangling rule (append `.mdx`). It does not mention result count limits or pagination, keeping it short of 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?

Purpose and usage come first, with the sibling-tool handoff at the end where it belongs. The parenthetical `head -200 /some/page.mdx` example is a bit verbose but earns its place by removing an inference the agent would otherwise have to make.

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 compensates by describing what a result contains (contextual content, titles, links) and how to get full page bodies. Complete enough to invoke correctly; only minor gaps around result volume and version-filter behavior remain.

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 both parameters are already documented in structured data. The description adds nothing about how to phrase the query or what the `version` filter accepts beyond the schema's example, so the baseline of 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?

States a specific verb and resource ('Search across the Cerebrium knowledge base') plus the content types covered (code examples, API references, guides). It also explicitly contrasts itself with the sibling query_docs_filesystem tool, so an agent can route correctly without opening either 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?

Gives explicit when-to-use conditions ('answer questions about Cerebrium, find specific documentation, understand how features work') and a clear escalation path: use query_docs_filesystem to head/cat the page when full content is needed. It even supplies the concrete `.mdx` path convention for that handoff.

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=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false, so the write/effect profile is covered. The description adds useful outcome context ('so the docs team can fix it') but says nothing about confirmation, rate limits, or what happens to submitted feedback, so it only marginally extends the structured data.

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?

Three tight sentences, front-loaded with the action and purpose, followed by trigger conditions and exclusions. Every sentence earns its place with no redundancy.

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 feedback tool with no output schema, the definition covers purpose, triggers, exclusions, and target audience completely. Annotations handle the mutation/effect profile, so nothing an agent needs to call this 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% and both parameters are well documented in the schema itself (path format, feedback content). The description adds no parameter-level detail beyond what the schema provides, so the baseline of 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?

States a specific verb+resource ('Report a problem with this documentation site') and makes the target explicit ('feedback about the documentation content itself'). It is clearly distinguishable from the read-only sibling tools query_docs_filesystem and search_sorsa_developer_platform, which retrieve rather than submit.

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?

Explicitly enumerates the triggering conditions ('incorrect, outdated, confusing, incomplete, or has a broken example') and adds clear exclusions ('not for product support requests or feedback about this tool or assistant'). This is a textbook when-to-use / when-not-to-use statement.

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