Add, remove, or list project annotations to document business rules, gotchas, and warnings, providing structured context for AI code assistants.
Add/remove/list project annotations (business rules, gotchas, warnings).
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | Text to add (required for add) | |
| index | No | Index to remove (required for remove) | |
| action | Yes | Action to perform | |
| category | No | Category (required for add/remove) |
Changes observed during successful MCP inspections.
v1.10.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits itself. It reveals the add/remove/list actions but does not explain whether modifications persist, are reversible, affect source files, or require any authorization. The 'remove' action especially lacks clarity about consequences.
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 a single front-loaded sentence that states the action and resource without wasted words. It is easy to scan and parse quickly.
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?
With no annotations, no output schema, and a mutation-capable tool, the description is too thin. It does not explain what happens after an add/remove, what 'list' returns, or how this metadata is stored or related to project files. An agent would need to guess about side effects and expected outputs.
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. The description adds a little meaning by explaining that the categories are business rules, gotchas, and warnings, but it does not provide additional semantics for text, index, or the conditional requirements between parameters beyond what the schema already states.
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 identifies the operation ('Add/remove/list') and the resource ('project annotations'), with concrete examples of annotation categories. It is immediately distinguishable from sibling file-reading and editing 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 purpose implies when to use it — whenever an agent needs to manage project-level annotations about business rules, gotchas, or warnings. However, it does not explicitly distinguish this from related editing tools like patch_file or replace_symbol, nor does it state when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.