What is known about one file

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

Annotations already declare readOnlyHint and idempotentHint, and the description adds real value on top: exactly what comes back (tasks with their dead ends and decisions, notes in full) and the path-resolution behavior. The note that absolute and relative paths fold to the same answer, so a note linked on one machine is found from another, is behavioral context an agent cannot infer from the schema.

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?

Four sentences, front-loaded with the payload description and followed by the when-to-use cue and the path/repo semantics. The aphorism about dead ends costing an afternoon is longer than strictly needed, but it carries the argument for calling the tool rather than being 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?

With no output schema, the description carries the return-value burden and discharges it by enumerating what is returned (tasks, dead ends, decisions, full notes). Combined with the path/cwd/project resolution rules and the calling trigger, an agent has everything needed to invoke this read-only tool correctly.

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 goes beyond the schema by explaining that `cwd` or `project` says which repository is being asked about, which is the non-obvious disambiguation when a path could resolve in several repos. It does not explain the `model` parameter at all.

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 names a specific resource and scope: everything todox has recorded against one file — tasks that touched it plus their dead ends and decisions, and the context notes attached to it in full. That aggregation is distinguishable from a single-note fetch, though no sibling (get_context, get_context_note, search) is named to sharpen the contrast.

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?

"Ask before editing a file you have not seen this session" gives a concrete triggering condition, and the cost/benefit framing (a dead end costs nothing to read and an afternoon to rediscover) reinforces why. It does not, however, state when NOT to use it or route to an alternative such as search or get_context_note.

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