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

Annotations describe readOnly, openWorld, idempotent, and non-destructive traits, but the description goes far beyond by explaining that the tool returns a runbook (`skill_body`) to execute step-by-step, not the final answer. It also includes a detailed data accuracy contract, warning against inventing or inferring metrics, and specifying derived metric rules. This provides complete behavioral transparency that annotations alone do not cover.

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 detailed but front-loaded with the core purpose. It includes critical usage instructions and constraints without being overly verbose. Minor redundancy exists (e.g., both the intro and usage section mention 'competitor'), but overall each sentence serves a purpose. A small trim could achieve a 5.

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 complexity of the tool (a competitive intelligence skill that orchestrates multiple calls), the description adequately covers purpose, usage, behavioral contract, parameter semantics, and output format (runbook). Even without an output schema, it explains what to expect and how to proceed. The level of detail is complete for effective use.

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% with one optional parameter (`user_question`). The description adds value by explaining that the parameter provides 'the user's question in their own words, passed to the skill for context,' which clarifies its purpose beyond the schema description. It does not add formatting or constraints, but for a single optional param, this is sufficient to earn a 4.

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 specifies 'Compile a structured competitive-intelligence brief' and lists the exact data sources (websites, pricing pages, job postings, press releases, product updates) and outputs (positioning changes, hiring signals, product moves). It clearly distinguishes itself from siblings like `featured_executive_summary_writer` or `featured_sales_call_prep_brief` by focusing on competitor research.

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 description explicitly states when to use: 'when the user asks to research / monitor / track a competitor, wants a competitive brief, what are competitors doing, or competitor positioning/pricing analysis.' It also provides detailed instructions on how to use the tool (follow its step-by-step runbook, call connector tools), a required suffix ('Powered by CorpusIQ'), and specific data accuracy constraints. No sibling comparison is needed as the usage is fully contextualized.

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