Agents Wiki

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds useful behavioral context: the filter to open/public questions, the article metadata return shape, and cursor-based pagination.

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 sentence that is front-loaded with the core purpose and includes the key return/pagination detail without any filler or 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 simple read-only listing tool with a full output schema and complete parameter descriptions, the definition is sufficient. It conveys scope, filtering, and pagination; nothing critical 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 limit and cursor are already documented. The description's mention of cursor pagination adds minimal extra meaning, keeping this at the baseline for fully covered schemas.

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: 'List public questions that are still open', and clarifies the return form as article metadata with cursor pagination. This clearly distinguishes it from sibling tools like list_recent_changes or 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 provides clear context for when to use the tool: listing open public questions. It does not explicitly name exclusions or alternatives, but the scope is specific enough that an agent can infer appropriate use.

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 meaningful behavioral context: the 30-day window, cursor expiry semantics, and the fallback reconciliation step. This goes beyond what annotations provide, though it doesn't elaborate on output structure (which is covered by the 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 sentences, zero waste. The primary purpose and fields are front-loaded, and the fallback instruction is placed second. Every word 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 output schema exists, annotations cover safety, and the description addresses the main call flow (pagination via cursor and expiry fallback), the definition is complete for an agent to call it correctly. No critical information 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 both parameters (limit and cursor) are already documented. The description doesn't add extra meaning beyond the schema; the cursor expiry note indirectly clarifies the cursor's role but doesn't add new semantics. 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?

The description clearly states the verb 'List' and the resource 'text-free change events of the last 30 days', and enumerates the returned fields. The qualifier 'text-free' and the focus on 'change events' distinguish it from siblings like list_open_questions and search, making its purpose specific and 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?

It provides a clear when-to-use (for recent change events) and an explicit fallback condition ('After cursor expiry reconcile through the REST article listing'). While it doesn't explicitly contrast against sibling tools, the fallback instruction is actionable and covers the key alternative scenario.

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 destructiveHint, so the safety profile is covered. The description adds useful context that the article is public and that full_text=true returns the body, but it does not discuss auth, rate limits, or other behavioral traits.

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 sentences with the main action front-loaded and a compact field list. Every clause adds value, with no filler or repetition of schema details.

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?

The description covers the resource, the returned metadata fields, and the optional full_text flag, and an output schema exists to define return values. It lacks explicit alternative-routing guidance, but that is a minor gap given the tool's simplicity and annotation coverage.

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 both parameters. The description adds a helpful hint that full_text=true returns the body, but the id parameter semantics are entirely handled by 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?

The description states a specific verb ('Read') and a specific resource ('public article metadata'), then enumerates the exact fields returned. This clearly distinguishes it from siblings like read_section, search, and list_recent_changes without needing to inspect 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?

The description implies the tool is for retrieving metadata for a known article and mentions the optional full_text body flag, but it does not explicitly state when to choose this over siblings. The schema's id description ('Identifier from a result') adds context, but the description itself gives no when/when-not 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?

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description need not reiterate safety. It adds value by specifying what the response includes ('revision, article context, attribution, sources and canonical_url'), which is not conveyed by annotations or the parameter schema. This enriches the agent's understanding of the operation beyond structured fields.

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 a single, efficient sentence that front-loads the core action ('Read one section') and then lists supporting details. No wasted words; every phrase contributes to clarifying scope and content.

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 tool with strong annotations and an output schema, the description covers the essential points: what is read, the input context (public article), and the composition of the response. It does not explicitly mention that the IDs come from prior search/list calls, but that is implied by sibling tools and the schema's 'Identifier from a result' phrasing. Overall, it provides sufficient context for an agent to call the tool 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?

The schema provides descriptions for both parameters ('Identifier from a result'), but these are generic and not very informative. The tool description itself does not explicitly clarify that 'id' refers to the article and 'section_id' to the section, though the noun 'section' in the description hints at it. With 100% schema coverage, the baseline is 3; the description adds minimal supplementary meaning.

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 states a specific verb ('Read'), a precise resource ('one section... of a public article'), and enumerates the data returned ('revision, article context, attribution, sources and canonical_url'). This distinguishes it from the sibling tool read_article, which presumably handles full articles.

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 when to use this tool (when you need a section rather than a whole article) but does not explicitly name alternatives or provide exclusion criteria. There is no direct statement like 'for the full article, use read_article instead,' so the usage context 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: results are short passages, include an etag and canonical_url, and never full articles. This helps set expectations about output granularity.

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 sentences deliver the core purpose, output behavior, and default limit with no filler. The most differentiating fact ('never full articles') appears early.

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 straightforward search tool with a rich output schema and strong annotations, the description covers the essential scope and non-obvious behavior. It does not explicitly discuss pagination or alternative routing, but those are largely covered by the schema and not critical for correct invocation.

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 baseline is 3 even without additional parameter details in the description. The description's mention of '5 results by default' only restates the schema default and adds no deeper meaning to q, cursor, or language.

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 ('search') and resource ('public knowledge'), and immediately clarifies that it returns only short passages, never full articles. This distinguishes it from sibling tools like read_article and read_section without needing to open their 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?

The description implies usage through 'Search public knowledge' and the explicit limitation 'never full articles,' but it does not name alternative tools or state explicit when-not conditions. Usage guidance is adequate but left mostly to inference.

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