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

Annotations mark this as a write operation (readOnlyHint=false) but do not detail error states. The description adds critical behavioral context: the tool will refuse to add a post that the user cannot read, and it will return a CONFLICT for duplicates. These are significant beyond what annotations provide. The note about 'read gate' explains a permission-related constraint. This makes the tool's behavior more predictable, earning a high score.

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 front-loaded with the core action in the first sentence. It consists of three short paragraphs, each with a distinct purpose: action, note guidance, and constraints. No redundant or irrelevant sentences. It could be further condensed (e.g., merging the last two sentences), but overall it is well-organized and efficient for its content.

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 has three parameters, an output schema (not shown but present), and annotations, the description covers the essential behavioral aspects: the operation, optional note usage, and two key error conditions (read-permission failure and duplicate conflict). It does not mention success responses or any rate limits, but the output schema likely handles the return format. This is sufficient for an agent to use the tool correctly in most scenarios.

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% with descriptions for all three parameters, so the baseline is 3. The description adds meaning to the 'note' parameter by calling it 'the part that makes a collection worth more than a list of links' and advising the user to 'say what the reader gets from this one.' For post_id and collection_id, it only echoes the schema's content ('the post's UUID' and 'Must be yours'). Since the description adds only modest extra value beyond the already-solid schema descriptions, a score of 3 is appropriate.

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 action: 'Append a post to one of your collections, with an optional note.' The verb 'append' and resources 'post' and 'collections' are specific. It distinguishes from sibling tools like colony_remove_from_collection by implication, but it does not explicitly contrast with them. The purpose is unambiguous, though a direct mention of the complementary removal tool would make it a 5.

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 guidance on when to use the optional note parameter: 'say what the reader gets from this one.' It also declares constraints: 'A post you cannot read reads as not found' and 'A post already in the collection is a CONFLICT,' which help an agent decide whether the tool is appropriate. However, it does not explicitly direct the agent to use colony_remove_from_collection for removal or colony_create_collection for creation, so it stops short of a 5.

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