Ankra Docs

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

Annotations already declare readOnly=true, idempotent=true, destructive=false, openWorld=false, and the description reinforces rather than contradicts them ("nothing runs on the user's computer, the server host, or any network", "No writes"). Beyond that it discloses non-obvious traits annotations cannot express: per-call STATELESSNESS with cwd resetting to `/` and no variable persistence, the 30KB output truncation limit, and the required batching strategy.

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 critical constraint that this is a sandbox, then bolded section headers (Workflow, paths warning), then examples — a structure an agent can scan. It is long, and a few lines are slightly redundant ("there is no separate 'get page' tool" overlaps with the workflow paragraph, and two of the seven examples repeat the same `head -80` shape), but nearly every sentence carries operational value for a free-form shell 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?

No output schema exists, yet the description covers return behavior (30KB truncation, what matches look like with `-C` context) and the downstream requirement to convert `.mdx` filesystem paths back to URL paths for citations. It also pins the OpenAPI mount path verbatim, which is the one piece of environment state an agent could not discover cheaply.

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 a single `command` param, so the schema baseline is already 3; the description substantially exceeds it by enumerating the supported command set (rg, grep, find, tree, ls, cat, head, tail, stat, wc, sort, uniq, cut, sed, awk, jq), the exclusions (no writes, no network, no process control), the `--help` escape hatch, and seven concrete invocation examples with real flag combinations.

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 ("Run a read-only shell-like query against a virtualized, in-memory filesystem") and immediately bounds scope: the filesystem contains ONLY Ankra documentation pages and OpenAPI specs. It also distinguishes itself from the sibling search tool by naming the exact conditions (keyword/regex, structural exploration, reading a page by path) where it wins.

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?

Explicit routing guidance is given in both directions: use search_ankra for "broad or conceptual queries like 'how to authenticate'" and this tool for exact matching or full-page reads. The "never guess paths" instruction with a concrete fallback (`rg -il "keyword" /`) and a worked example of the wrong-path-picked failure mode is exactly the when/when-not guidance an agent needs.

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, idempotentHint, and closed-world scope, so safety is covered. The description adds real behavioral context beyond that: it describes the shape of the response (contextual content with titles and direct links) and documents the follow-up workflow for retrieving full page bodies. It stops short of stating result-count limits or ranking behavior, which keeps 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 purpose, then usage conditions, then the cross-tool handoff — a sensible ordering. The parenthetical `.mdx` example is long but genuinely operational, so it earns its place; otherwise the prose is tight with little 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 one-parameter search tool whose safety profile is fully annotated and which has no output schema, the description covers purpose, when to call it, what comes back, and how to escalate to full content. Nothing an agent needs in order to call it correctly and follow up 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?

There is a single required parameter and the schema already describes it at 100% coverage, so the baseline is 3. The description gives no query syntax, phrasing, or keyword guidance that would help an agent craft a better search string, so it adds no meaning beyond the schema.

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 Ankra knowledge base') and enumerates the content types it covers (information, code examples, API references, guides). It also distinguishes itself from the sibling query_docs_filesystem tool, so an agent can route between the two without opening a 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?

Explicitly lists the triggering situations — answering questions about Ankra, finding docs, understanding features, locating implementation details — and then names the alternative tool and the condition that selects it (needing full page content). The handoff instruction includes the concrete `.mdx` path convention, leaving nothing to inference.

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.