inspect_trace

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower. The description adds a genuinely useful interpretive constraint — 'Absence of events does not establish absence of execution' — which prevents an agent from over-reading empty results. It says nothing about how pagination interacts with that coverage claim, costing it the top score.

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 tight sentences with no filler, and the core action is front-loaded. The only weakness is the compressed jargon in the second clause, which reads as terse rather than clear.

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 read-only inspection tool with four parameters and no output schema, the description is adequate but thin: it never explains what a 'trace summary' contains, what 'hook coverage' means, or how paged results relate to the aggregate summary. An agent knows the general shape but not what to expect back.

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 only 25%, so the description must compensate but largely doesn't. It implies paging via 'paged hook coverage','but doesn't say what limit/offset page over, and adds no detail on trace_id format or analysis_project_id retention behavior beyond the schema's own text.

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 ('Inspect one trace summary') plus the content it returns (hook coverage, installed/pending/failed states, overload/loader identities). This distinguishes it from data-fetching siblings like get_trace_events, though the dense noun stacking ('concrete overload/loader identities') makes the resource somewhat hard to parse.

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 only implied: pick a trace_id and inspect it. No explicit when-to-use versus get_trace_events or list_evidence, and no prerequisites or exclusions beyond the epistemic caveat. The caveat about absence of events is a caution, not routing guidance.

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