Internal link opportunities

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value beyond annotations with 'It never invents destination URLs' — a meaningful behavioral constraint about output trustworthiness. However, it doesn't disclose output format or what happens when the inventory is empty, though with rich annotations this is acceptable.

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. Each sentence earns its place: the first states the action and mechanism, the second adds a trustworthiness guarantee about behavior. Front-loaded and extremely efficient.

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 has 2 params (1 required), candidate_links contains nested objects with keywords, and there's no output schema. The description covers the core contract well: audit existing links, match to supplied inventory, never invent URLs. It could mention what the output looks like (since there's no output schema), but given the read-only, idempotent annotations and the relative simplicity of the tool, it's largely complete for the agent to select and approximate usage 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 only 50%, so the description must compensate partially. The description explains the core mechanism — matching page topics to the supplied inventory — which directly clarifies the purpose of candidate_links. The 'never invents destination URLs' clause reinforces that url and candidate_links work together. The 'Audit existing internal links' phrase adds context for the url parameter that the schema's minimal 'Public webpage URL' doesn't provide.

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 ('Audit') and the resource ('existing internal links'), and explains the specific method: matching page topics to a supplied inventory of real internal URLs. The statement 'It never invents destination URLs' is a powerful clarification given the sibling tools (many bing_* tools retrieve data, while aeo tools audit aspects). This distinguishes it well from aeo_internal_duplicate_check and other aeo audit tools.

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 that this tool works on a supplied inventory of URLs, and the 'never invents destination URLs' phrase signals that users must provide the candidate URL inventory (the candidate_links parameter). It's clear this is a read-only audit. However, it doesn't explicitly state when to use it vs alternatives like aeo_internal_duplicate_check or list cases where it should not be used, though the sibling distinctions are reasonably inferable.

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