Inspect persisted shared work state to retrieve current project status without appending a polling event. This read-only check provides real-time visibility into the Entroly context engine's work progress.
Inspect persisted shared work state without appending a polling event.
| Name | Required | Description | Default |
|---|---|---|---|
| now_ms | No | ||
| project | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v1.0.62Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It does disclose the most important trait — that this operation inspects rather than mutates and deliberately avoids appending a polling event. However, it stops there: no mention of freshness guarantees, locking behavior, or failure modes. The key trait is disclosed but the behavioral picture is thin.
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?
A single 12-word sentence that front-loads the verb and resource, then adds the one behavioral caveat that matters. Every word earns its place; there is no filler or repetition of schema contents.
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 simple read tool with an output schema present, the description covers the core behavior. But it misses parameter semantics (now_ms and project are unexplained) and never names the counterpart tool for the polling-event case it distinguishes itself from. Adequate for a trivial tool, but with identifiable gaps.
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%, so the description must compensate for unclear parameters — but it says nothing about now_ms or project. The names hint at meaning ('now in milliseconds', 'project'), yet the description never clarifies what a 0 default means for now_ms, whether project filters results, or how they interact. This is a genuine gap for a low-coverage tool.
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 uses a specific verb ('Inspect') and resource ('persisted shared work state'), and adds a behavioral differentiator ('without appending a polling event') that sets it apart from state-mutating siblings like work_claim, work_resume, and work_handoff. An agent can immediately tell this is a side-effect-free read of shared state.
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?
The 'without appending a polling event' clause implies the appropriate use case: check state when you do NOT want to create a polling side effect. However, no alternative tool is named, and there is no explicit statement of when NOT to use it or which sibling to choose when a polling event IS acceptable. The guidance is implied rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.