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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile, so the bar for additional disclosure is lower. The description adds modest behavioral context — this is a 'contract' returning 'the full record' as opposed to search snippets — but it does not disclose error behavior, not-found handling, or any response characteristics beyond completeness.

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 no real waste, and the actionable detail — ID format and return value — is front-loaded in the second sentence. The opening clause ('OpenAI ChatGPT Deep Research / Connectors fetch contract') partially duplicates the title 'Fetch (OpenAI Connectors)', a minor redundancy, but overall the definition is appropriately sized.

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 single-parameter, read-only tool with an output schema present, the description is nearly sufficient: it covers the input format, the source of the id, and the purpose of the return value. The gaps are minor — no statement about what happens when an id is invalid or not found, and no explicit differentiation from the get_* siblings — but nothing critical is missing for basic 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 0%, so the bare schema offers only a string with min/max length; the description carries the full burden and largely succeeds. It specifies the exact accepted formats ('artist:<uuid>', 'campaign:<uuid>', 'smartlink:<uuid>') and the parameter's provenance (returned by search), which is precisely what an agent needs to construct a valid call. It stops short of saying whether other prefixes are possible, leaving a small edge-case gap.

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 (returns), resource (full record), and the precise input contract (id formatted as 'artist:<uuid>', 'campaign:<uuid>', or 'smartlink:<uuid>'). This materially distinguishes fetch as a cross-entity retrieval tool versus the more specific dynamoi_get_campaign, dynamoi_get_smart_link, and other get_* siblings, though it never explicitly names those alternatives.

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 establishes an implicit usage precondition: the id must come from `search`, tying the two tools into a workflow. The phrase 'for citation' hints at the intended downstream use case. However, it gives no explicit when-to-use/when-not-to-use guidance versus the many dynamoi_get_* sibling tools, so an agent must infer the routing decision.

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