Celo Docs

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

Annotations already declare readOnlyHint, idempotentHint, closed-world and non-destructive, and the description adds genuinely non-obvious behavior on top: full statelessness between calls (cwd resets to `/`, no shell variables), a 30KB truncation ceiling per call, and a documented command allowlist with no writes/network/process control. These are exactly the traits that cause agent errors and none are recoverable from the 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?

Structure is strong — bolded caveats, a workflow paragraph, an examples block, and output-limit guidance — so the critical facts are front-loaded. Some redundancy is present, e.g. 'NOT a shell on any real machine' is restated as 'nothing runs on the user's computer, the server host, or any network,' which could be tightened without losing meaning.

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?

No output schema exists, and the description compensates by explaining the truncation limit, how to get context around matches via `rg -C`, how to batch reads, and how to convert returned `.mdx` paths back to URL paths for the user. For a one-parameter sandbox query tool, nothing an agent needs in order to call it successfully 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 single `command` parameter is already documented, but the description goes further by enumerating the supported command set (rg, grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq) and showing five concrete example invocations, which materially constrains how the parameter should be formatted. It stops short of documenting syntax edge cases like quoting or escaping rules, so not a 5.

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: running read-only shell-like queries against a virtualized filesystem containing only Celo Docs pages. It explicitly clarifies what the tool is not (a real shell) and distinguishes itself from the sibling search tool by naming the cases it uniquely serves (exact regex, structural exploration, full-page reads).

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 an explicit routing rule: use search_celo_docs for broad/conceptual queries, use this tool for exact keyword/regex matching, tree/ls exploration, or reading a known page. It also names the alternative and the failure mode — a missing path does not mean the topic is undocumented, so use `rg -il` instead. That is a complete when/when-not/alternatives picture.

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 the safety profile (readOnly, idempotent, closed-world, non-destructive), and the description adds meaningful behavior: results come back as contextual snippets with titles and direct links rather than full pages. It also reveals the useful workflow detail that returned paths are read via `head`/`cat` with a `.mdx` suffix appended. Slightly muddied because part of that guidance describes the sibling tool's usage rather than this one's.

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 purpose, then usage triggers, then return shape, then the handoff to the sibling. The `.mdx`/`head -200` parenthetical is longer than needed and drifts into the sibling's territory, but it is actionable rather than filler.

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 no output schema, the description covers purpose, retrieval scope, result shape (titles plus direct links), and the follow-up path for full content. An agent has everything needed to call it correctly and to route results onward.

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% and there is only one parameter, so the schema already carries the burden. The description does not clarify query semantics (natural language vs. keyword, phrase handling, whether code snippets can be searched), which is the one thing it could add beyond the one-word 'Search query' schema text.

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 Celo Docs knowledge base') and enumerates what it retrieves: information, code examples, API references, guides. It is clearly distinguished from the sibling query_docs_filesystem_celo_docs, which is framed as the follow-up for full page content.

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 triggers ('answer questions about Celo Docs', 'understand how features work', 'locate implementation details') and an explicit alternative with its condition: use query_docs_filesystem when the full page content is needed. Nothing is left for the agent to infer.

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.