stale_todos

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

With no annotations, the description carries the full burden and does disclose real behavior: the classification rules that map results to min_commits and active_window, and the hard prerequisite that a git repository is required. It does not state read-only/safety profile or how results are ordered/limited, but the core behavioral contract (how items are bucketed) is unusually well exposed.

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 definition is front-loaded with the central idea and the classification scheme, then the format rule and the git prerequisite. The long parenthetical is slightly run-on, but every clause conveys substantive information with no filler.

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?

An output schema exists, so return values need not be explained, and the bucketing semantics are covered well. But for a six-parameter tool with zero annotation and zero schema-description coverage, the undefined markers, repo, and limit parameters leave an agent guessing on inputs it must supply.

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 0% across six parameters, so the description must compensate. It explains the duration syntax (90d/12w/6m/2y) for older_than and active_window, and implicitly defines min_commits via the 'hot' rule, but leaves markers (which marker strings?), repo (path vs. default), and limit entirely undefined.

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 gives a specific resource and operation: old markers (TODOs) classified by whether their file is still active, with three named buckets ('hot', 'cooling', 'dead'). It is reasonably distinct from a plain listing, but it never names or contrasts itself with siblings like list_todos or todo_history, so an agent must infer the boundary from the name alone.

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?

Usage is implied rather than stated: the parentheticals ('fix or delete it', 'candidate for removal') tell the agent what each bucket means actionably, which helps interpret results. However, there is no explicit statement of when to call this instead of list_todos, todo_history, or hotspot_debt, and no exclusions or prerequisites beyond 'Needs a git repository'.

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