Faceabot Wikipedia

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive. The description adds pagination behavior (pages up to 20,000 characters, use start to read further) and output format (plain text), which are useful beyond 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?

Three compact sentences: the core description, the usage condition, and a concrete example. It is front-loaded with the key behavior and contains no wasted wording.

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 retrieval tool with annotations covering safety and no output schema, the description clearly covers what is returned (full plain text, paginated) and how to continue reading. It omits edge cases like missing pages or redirects, but nothing critical 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 coverage is 75% and the schema documents title, lang, and start. The description adds an example with title, lang, and max_chars, and explains page size and start usage in prose. It partially compensates for the missing max_chars description, though it does not explicitly state that max_chars sets the page size.

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 resource (one Wikipedia article) and output (full text as plain text), and explicitly distinguishes itself from the summary sibling by adding 'beyond the summary'. An agent can tell this is the full-article reader, not a summary or search tool.

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?

Provides a clear use condition ('you need details beyond the summary') which implies when to choose it over wiki_summary. It does not explicitly name wiki_search as an alternative or state when not to use it, but the routing is clear enough.

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, destructive=false and openWorld, so the safety profile is covered. The description adds genuinely new behavioral information: this is a discovery tool returning titles, one-line descriptions and excerpts rather than page content, which matters because there is no output schema to reveal that.

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 short, front-loaded sentences: what it does, when to use it, then a concrete invocation example. Nothing is padded, though the example is somewhat redundant given the schema already names both parameters.

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 the return format, and annotations cover the safety profile. Language coverage ("in any language") and the example invocation are present, so an agent has everything needed to call it 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 67%, with lang well documented in the schema and the unbounded "results" parameter carrying no description in either place. The description's example illustrates query and lang usage, but it adds no meaning beyond the schema fields, so it sits at the baseline for partial coverage.

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 Wikipedia") plus the return shape (matching page titles with a one-line description and an excerpt). It is clear on its own, but it never distinguishes itself from the sibling tools wiki_article and wiki_summary, which is exactly the ambiguity an agent faces here.

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 "Use when: you need to find the right Wikipedia page for a topic, person, place or concept" clause gives explicit selection context, and the example shows the tool being called. However, it offers no exclusions and never routes the agent away from wiki_article or wiki_summary when a full page or summary is what's actually wanted.

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, openWorld and non-destructive, so the safety profile is covered. The description adds value beyond that by enumerating the returned payload (lead paragraph, page description, last edit time, link), 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?

Three short lines: purpose, usage trigger, concrete example. Front-loaded and free of filler, though '(lead paragraph)' is mildly redundant with 'short summary' and the format could be tightened further.

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 read tool with no output schema, the description covers the payload adequately and the schema fully covers the inputs. Minor gaps remain around disambiguation/redirect handling and failure behavior, but nothing essential 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 are already documented, including the 'use wiki_search first if unsure' caveat. The embedded example confirms the required title/lang shape but adds no semantics beyond the schema — 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?

States a specific verb+resource (short summary / lead paragraph of one Wikipedia page) and enumerates what comes back: description, last edit time, link. It implicitly contrasts with wiki_article (full article) by emphasizing 'short summary (lead paragraph)', but never names the siblings explicitly, so an agent must infer the boundary.

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?

'Use when: you need a quick, sourced overview of a topic' gives a clear selection context. It stops short of stating when NOT to use it or pointing to wiki_article/wiki_search as alternatives — that routing hint only appears in the schema's title description, not the tool description.

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