Update Unsplash Collection

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description is consistent with them, adding real behavioral value beyond the annotations: the partial-update semantics 'Only the fields you pass are changed' informs the agent this is PATCH-like behavior rather than replace-all, and the explicit OAuth login prerequisite surfaces a likely failure mode. The redundant fragment 'Not read-only.' restates what readOnlyHint=false already conveys, which prevents this from reaching a 5. No contradiction with 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?

The description is efficient and front-loaded: the main purpose comes first, the critical partial-update semantics second, and the auth prerequisite last. Every clause earns its place except the final 'Not read-only.' fragment, which duplicates the information already carried by readOnlyHint=false in the annotations — a minor redundancy. The login command with an example adds legitimate practical value.

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 mutation tool with 4 simple parameters, one required, and a full schema, the description covers everything an dimension agent needs to call it correctly: the purpose, the ownership scope, the partial-update field-behavior, and the only prerequisite (OAuth login). No output schema exists, but none is strictly necessary for a straightforward update tool whose success is simply the persisted changes. No equivalent gaps like on boarding the no-op failure modes that the auth hint already covers.

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 100%, so the baseline is 3 — each parameter (id, title, private, description) is already documented in the schema. The description adds meaningful semantic context beyond that: by stating 'Only the param fields you pass are changed,' it tells the agent that title, private, and description are optional partial updates and that omitting them is safe, which is not explicitly stated in the schema itself. This enrichment raises it one rung 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 states a clear verb and resource combination: 'Update a collection owned by the authenticated user.' The ownership constraint differentiates it from sibling tools like unsplash_create_collection, unsplash_delete_collection, and other update tools (unsplash_update_photo, unsplash_update_my_profile) with no ambiguity. The scope qualifier 'owned by the authenticated user' also tells an agent this only applies to the user's own collections, which is a meaningful restriction.

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 gives clear context for when to use it: editing a user's own existing collection, including the explicit prerequisite 'Requires OAuth sign-in — run npx @hanoak/unsplash-mcp-server login first.' The ownership wording implies the exclusion (you cannot update collections you don't own), but it doesn't explicitly name a sibling alternative or state a when-not-to-use case. A clear operational trigger with prerequisites is present, so this falls short of the full 5 which requires explicit exclusions.

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