Cyber Library

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed world), so the bar is lower. The description adds operationally useful facts the annotations lack: the 400-entry cap, the whole-library default, and the indented output shape.

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 what the tool returns and its scope, then usage, then the cap. No filler; the docs link is the only boilerplate.

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 does state the return format (indented outline) and the cap, which is the key operational caveat. It omits what happens on truncation at 400 entries and any ordering guarantees, but is otherwise sufficient for a read-only, closed-world tool.

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 path/depth/locale semantics and defaults are already documented in the schema. The description restates the whole-library default and depth scoping but adds no syntax or edge-case detail beyond it.

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?

Specific verb+resource: an indented outline of the library tree beneath a path, with scope (default whole library) and depth. It implies a read-before-explore role but does not explicitly differentiate itself from list_topics or get_planned_subtree, which also enumerate tree structure.

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?

"Useful to understand how a domain is organized before reading pages" gives a clear moment to reach for this tool, implicitly routing the agent away from get_page. It stops short of naming sibling alternatives (list_topics, get_planned_subtree) or stating exclusions.

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 cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower. The description usefully adds what is returned (markdown body, title, URL, breadcrumbs, last update, contributors, child pages for folders), which the annotations do not convey.

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 dense, front-loaded sentences with a concrete path example and a docs link. Slightly packed but every clause carries information an agent needs.

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?

Covers return shape, input formats, and a docs pointer; no output schema exists, so describing the payload is appropriate. It could say more about the tool's place relative to its list/search siblings.

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 a concrete path example and notes full URLs are accepted, but locale and max_chars semantics are left entirely to 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 (Returns) and resource (a page of the Cyber Library) plus the exact return payload (markdown, metadata, child list). It's clearly distinguished from siblings like get_outline, search_library, and list_topics by being the single-page reader.

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 implies usage by explaining path format and URL acceptance, but never states when to use this tool versus siblings like search_library or list_topics. A 'use this to fetch a known page' framing would be needed for a 4.

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 and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the 400-entry cap (a size/truncation limit) and the per-topic fields returned (kind and status), which the agent could not derive 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?

A single front-loaded sentence carries the resource, the source of the id, the return fields, and the cap; the trailing docs link is short and useful. Minor redundancy with the schema's own 'omit for the Cyber root' wording costs a point but nothing is bloated.

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 must convey return content, and it does: an outline structure annotated with kind and status, plus a truncation cap. The only real gap is an explicit statement of how this subtree differs in content from the published outline returned by get_outline.

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 the schema already documents both parameters, including the 'omit for the Cyber root' note that the description repeats verbatim. The description adds no syntax, format, or depth-behavior detail beyond the schema, so the baseline 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?

Names a specific resource (the planned taxonomy subtree) and the verb-like action (outline), and states what each entry contains (kind and status). It differentiates itself from the published-taxonomy sibling get_outline only implicitly via the word 'planned', and never names get_outline as the contrasting alternative.

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?

Tells the agent where the topic_id comes from (search_planned_topics) and the special case for omitting it (Cyber root), giving clear entry context. It does not explicitly state when to prefer this over get_outline or list_topics, so the when-not side is left 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is low. The description earns credit by disclosing the returned fields (title, path, sub-page count, description) in the absence of an output schema, plus a docs URL for deeper detail. It adds no pagination or rate-limit context, 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?

One dense sentence that front-loads the action and scope, followed by a docs link. Nothing is wasted, though the trailing URL is marginally promotional rather than operational.

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 read-only, argument-optional listing tool with full schema coverage, this is nearly complete: it explains the default behaviour and enumerates the return fields, compensating for the missing output schema. The only gap is routing guidance against search and outline siblings.

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 the schema already documents both parameters, including 'omit for the top level'. The description's only parameter-relevant statement restates that. Baseline 3 applies; the 'six top-level sections' detail is output-side, not parameter semantics.

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 ('Lists the direct children of a folder of the library') and pins the scope with 'direct children' plus the no-path fallback to the six top-level sections. It does not name the sibling tools it overlaps with (get_outline, search_library), but the scope constraint alone is enough to tell it apart.

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?

It clarifies the one conditional usage case (omit path to get the top level), which is genuinely useful. However, it never says when to prefer this over get_outline or search_library, so the agent must infer the browsing-vs-searching split from sibling names.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real value beyond that by disclosing what is searched (titles, descriptions, paths) and what is returned (path and URL), which matters because there is no output schema.

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 compact sentences plus a docs URL, with the core scope front-loaded and the chaining hint immediately after the return-shape statement. No filler sentences.

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 correctly compensates by describing the return payload (matches with path and URL) and the handoff to get_page. Remaining gaps are minor: no mention of result-set behavior relative to the limit cap or locale effects, though both are documented in the schema.

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 limit, query and locale all documented inline including examples and defaults, so the schema does the heavy lifting. The description adds only marginal meaning by clarifying that matching runs against titles, descriptions and paths; baseline 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?

States a specific verb and resource ('Full-text search over the published pages of cyberlibrary.com') and enumerates the searched fields (titles, descriptions, paths). The 'published pages' scope implicitly separates it from sibling search_planned_topics, and the description makes the tool's output concrete (best matches with path and URL).

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 clear follow-up context: 'pass a path to get_page to read it,' which routes the agent into the correct next tool. It does not, however, state when to prefer this over search_planned_topics or list_topics, so the alternative-selection guidance is implied rather than explicit.

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, non-destructive, closed-world), so the bar is lower. The description still adds real value: it discloses the 8k+ dataset scope, that drafts are included, and that results carry status and position fields. It omits pagination/ordering behavior, but for a read-only search this is a solid addition beyond the structured metadata.

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 tightly written sentences plus a docs link, with the scope and draft-inclusion qualifier front-loaded before the alternative-tool hint. Every clause carries information; nothing is 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?

There is no output schema, so the description usefully names the returned fields (status and position) and the dataset scope, which is enough for an agent to interpret results. Minor gaps remain around result ordering or maximum effective result count, but nothing essential 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 description coverage is 100%, so the schema already documents query, limit, and status. The description corroborates the status values (draft, review, ready, generated, published) but adds no syntax, matching, or ranking detail beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (searches the structure database snapshot of the Cyber taxonomy) and quantifies scope (8k+ planned topics). It explicitly distinguishes itself from published-content siblings by noting it covers 'drafts not yet published on the site', so an agent can separate it from search_library 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?

Gives clear context for when this tool applies (searching the planned taxonomy including drafts) and names the follow-up alternative, 'Use get_planned_subtree with an id to explore around a match.' It does not explicitly state when to prefer search_library over this, so routing between the two search tools is left partly to inference.

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