Generate a scatter plot of two pulsar-wind-nebula properties, colored by PWN class, with automatic logarithmic axes for wide data ranges.
Scatter plot of two properties of the bundled PWNe, coloured by PWN class (e.g. Ė vs τ_c, PWN size in pc vs age). Physical sizes use the ATNF distance. Axes go logarithmic automatically when the data span more than two decades.
| Name | Required | Description | Default |
|---|---|---|---|
| x | No | char_age_yr | |
| y | No | edot_erg_s | |
| log_x | No | ||
| log_y | No |
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 carries the full burden and does disclose two useful behaviors: distances come from ATNF and axes auto-switch to log past two decades. It omits what the tool actually returns (figure object, saved file, inline image), whether all bundled PWNe are always plotted, and what explicit log_x/log_y values override.
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 tightly packed sentences with the plotting action first and the caveats (distance source, auto-log) after. Efficient, though the parenthetical examples and the physics notation add density that an unfamiliar agent must parse.
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-param visualization tool with no annotations and no output schema, the description should state the return artifact and the dataset scope ('bundled PWNe' is undefined). It covers plotting semantics adequately but leaves an agent guessing about the response.
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 0%, so the description must compensate. It does explain that x/y are selectable physical properties, that physical sizes depend on ATNF distance, and that log axes are auto-chosen — but the log_x/log_y booleans, their null default, and the default x/y pair are never addressed.
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: a scatter plot of two chosen properties of the bundled PWNe, colored by PWN class, with concrete axis examples (Ė vs τ_c, size vs age). It is clear what the tool produces, but it never distinguishes itself from siblings like plot_ppdot or plot_cmf_comparison, which appear to be special-cased population plots over the same data.
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 shown only through example axis pairs, implying 'use this for exploratory correlations.' There is no statement of when to prefer plot_ppdot or another sibling, and no mention of prerequisites or data scoping.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.