weeek_manage_projects

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

No annotations are provided, so the description carries the entire burden of behavioral disclosure. It lists the action types but doesn't disclose side effects: what happens to tasks in an archived project, whether delete is permanent or reversible, permission requirements, or whether dependent resources get cascaded. For a mutation tool with five distinct destructive/non-destructive actions, this is a significant gap.

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 efficient sentences, zero filler. Front-loaded with the full action list and immediately points to the read sibling. Could arguably add one sentence of behavioral context (e.g., 'Archive and delete have different task implications'), but overall it's well-structured and skimmable.

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?

This is a complex multi-action CRUD tool (5 actions) with no output schema and no annotations, yet the description is a single-line action list. It doesn't clarify return values per action, prerequisites (e.g., portfolio_id required for create), or the distinct semantic weight of archive vs unarchive vs delete. For a tool of this complexity, the description under-delivers on the behavioral contract, though schema descriptions offset some of it.

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 71%, so most parameters (name, color, project_id, is_private, action, portfolio_id) have their own descriptions. The tool description adds no beyond-schema value for parameters. The description adds the 'Required on update' nuance for color, but that's already in the schema. Baseline 3 is appropriate since schema handles most of the work, though the ~29% undocumented remainder (description param) is a minor 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?

Clear action verb 'Create, update, delete, archive or unarchive' with explicit resource 'a project'. Distinguishes from sibling read tool weeek_list_projects. Purpose is well defined and unambiguous, though it doesn't enumerate all operations' effects distinctly.

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?

Description explicitly points to weeek_list_projects for reads, establishing a clear read-vs-write boundary. However, it doesn't provide exclusions for when NOT to use this tool vs other manage_* siblings (tags, boards, columns, portfolios), nor scenarios like when project deletion is preferable to archiving.

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