perf_annotate

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

With no annotations, the description carries the full burden. It discloses the output format (source/assembly listing with % annotations), the key requirement (debuginfo for source interleaving), and compatibility (works on any perf.data). It doesn't explicitly state it's read-only, but the verbs 'shows' and 'annotation' strongly imply a non-mutating analytical operation. The provided behavioral details (output, requirements) go beyond the bare minimum.

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?

The description is front-loaded with the purpose, then provides usage context, key parameters, output, and requirements. It is organized with a 'Key parameters:' section and uses concise bullet-like formatting. While it lists seven parameters, each earns its place by clarifying important defaults or options. It remains reasonably compact for a tool with 33 parameters.

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?

Given the tool's complexity (33 params), the description covers the essential workflow, key parameters, output, and dependency (debuginfo). The output schema exists, so return values are already specified. The only minor gaps are not discussing every parameter or potential limitations (e.g., permission requirements), but the schema covers parameter details. Overall it provides enough context for an agent to invoke the 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 adds meaningful semantic context for several key parameters: symbol (default: hottest), dsos (restrict to binary/library), source (interleave source), disassembler_style (Intel vs AT&T), percent_type (enumerating options), data_type, and code_with_type. These enrich the terse schema descriptions, especially for percent_type where the schema only says 'Percent type.'

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 opens with 'Source/assembly annotation: shows per-line or per-instruction sample percentages inside a specific function.' This clearly states the verb (shows), the resource (source/assembly annotation with percentages), and the specific scope (inside a specific function). It also differentiates from siblings by positioning it as a follow-up to perf_report for drilling into hot functions.

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?

Explicitly says 'Use this after perf_report to drill into a hot function,' giving clear workflow context. It doesn't explicitly list alternatives or exclusion cases, but the 'after perf_report' instruction implies its role relative to sibling tools. The description also notes requirements (debuginfo packages) which further guides when to use.

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