Project todos

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

Adds genuine context beyond the annotations: todos persist across sessions and surface in project_brief, which is the key behavioral property of this store. However, it is silent on the mechanics an agent would want for a mutable 8-param tool — how list is bounded (limit defaults to 30, max 100), whether duplicate titles are rejected, and what done actually does to the record.

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?

One compact sentence-per-action block, front-loaded with the resource and then the action contract. Every clause carries either a required-parameter rule or an alternative, with no padding.

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 4-action, 8-parameter mutation tool with no output schema and thin annotations, the description leaves too much open: list's return shape and pagination, the meaning of tags/content/importance, and whether reopening restores prior state. An agent could call the wrong action with the wrong parameters and only discover it from errors.

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 only 25%, and the description covers just the two that already have schema text (title, id) plus include_done. Four parameters — tags, limit, content, importance — are undocumented in both schema and description, including the limit that governs list output size and the importance score that presumably affects ordering.

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?

States a specific verb and resource ("Manage the durable project todo list") and enumerates the four supported actions with their semantics. It is distinguishable from the memory siblings (remember/recall/forget) by the 'project todo' framing, though it never names them explicitly.

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?

Gives per-action conditions (title for add, id for done/reopen, include_done for list), which is real routing guidance within the tool. It stops short of saying when to use this versus remember/forget/context_pack, so an agent must infer the boundary between durable todos and memory entries.

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