Edgepedia

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 useful behavioral context about the `citations: false` output format and instructs to link the article and show the credit line, which is helpful beyond the annotations. It doesn't describe response format details, but an output schema exists.

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 one dense but well-structured paragraph; the core action is front-loaded and the details are efficient. A slightly clearer break between what the tool does and how to use the result would improve skimmability, but there is no wasted text.

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 tool is a read-only fetch with an output schema and full parameter coverage. The description covers input origin, the citation-reduction option, and how to handle the result, leaving nothing material missing for an agent to invoke 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 description coverage is 100%, so the schema already documents both parameters. The description adds the practical behavioral meaning of `citations: false` (text about a quarter shorter, [n] markers, reference list kept), which is valuable beyond the schema's default note. That justifies a 3.

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 uses a specific verb with a specific resource ('Get one Edgepedia article in full, as Markdown with its citations') and ties the id to a `search` result, which differentiates it from the sibling search tool. The scope is clear 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 explicitly says the id comes from a `search` result, giving clear context for when to use it. It does not explicitly state when not to use it (e.g., when only a snippet is needed), but the linkage to search results is strong practical 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description doesn't need to restate safety. It adds behavioral context beyond annotations: the matching algorithm (titles, other names, misspellings, not full text), the return limit (up to 10 results), and that results include opening sentences. This enriches the agent's understanding of how the tool behaves, though it doesn't cover error cases or edge conditions, so a 4 is appropriate.

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 three sentences with zero filler. The first sentence states the purpose and scope, the second provides imperative usage instructions, and the third covers output and next steps. It is front-loaded and every sentence earns its place, making it efficient for an agent to parse.

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 tool's single parameter, the presence of an output schema, and comprehensive annotations, the description covers all essential aspects: what to search, how to phrase the query, what it returns, and how to proceed with the results. No critical information is missing for an agent to invoke this 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?

Schema description coverage is 100% for the query parameter, giving a baseline of 3. The description adds meaningful semantics beyond the schema: it explicitly says to pass the subject's name (not a question) and explains that it matches titles, aliases, and misspellings. This helps the agent formulate queries correctly, pushing the score above baseline.

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 ('look up') and resource ('Edgepedia'), and explicitly distinguishes itself from the sibling 'fetch' by instructing the agent to pass a result's id to fetch for the article. It also scopes the search to people, places, things, events, or concepts, so an agent knows exactly what this tool does and how it differs from the only sibling.

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 explicit usage guidance: pass a subject's name, not a question; it matches titles, aliases, and misspellings, not full text. It also tells the agent to use 'fetch' for full articles after receiving a result id, effectively routing to the alternative. This is clear when-to-use and when-to-use-another guidance.

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