Fetch a specific section (summary, files, diff, commands, or trace) from a past task's report to save tokens, requesting only the part you need.
Fetch one part of a past task's full report. Only when needed: it costs Claude tokens.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No | For section=diff: one file | |
| section | Yes | ||
| task_id | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry the behavioral load. It usefully warns of token cost, but discloses nothing about response size, whether sections are cached, what happens with an invalid task_id, or that section=diff requires the path param.
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 short sentences with the purpose front-loaded and no filler. The cost caveat is terse to the point of being slightly ambiguous ('it costs Claude tokens'), but nothing is wasted.
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?
A 3-param tool with a 5-value enum, no annotations, and no output schema. The description leaves the agent guessing what each section returns and how 'path' interacts with section=diff, which is a meaningful gap.
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 only 33%: only 'path' is documented, and it is JSON-encoded, not human-readable. The five enum values for 'section' are never explained in the description, and task_id gets no guidance at all, so the low-coverage gap is not compensated.
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+resource: fetch one section of a past task's stored report. It clearly separates report retrieval from the ask/task siblings, though it never names those siblings 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?
'Only when needed: it costs Claude tokens' gives a soft usage constraint and a cost signal, but no concrete condition for when to prefer deepseek_task or deepseek_ask over pulling a report section, and no exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.