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

Annotations declare openWorldHint=true, readOnlyHint=false, destructiveHint=false. The description adds valuable behavioral context: it 'never adds facts not in the source' (faithfulness guarantee) and openly warns it 'SPENDS your balance -- requires authentication (OAuth)' — critical financial and auth disclosure not captured in annotations. It does not describe output structure, but output_schema exists and covers that.

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 two sentences and front-loaded with the purpose, then quickly pivots to critical behavioral warnings (faithfulness, cost, auth). It's compact and every sentence earns its place. Minor verbosity in the format list, but overall efficient.

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 2-param tool with full schema coverage and an output schema present, the description covers purpose, input flexibility, faithfulness, cost, and auth. The main gap is not explaining return value granularity (e.g., what summary vs executive summary vs bullet points means), but the output schema partially covers structure. Given the tool's moderate complexity plus cost/auth transparency, this is well covered.

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 schema already documents both parameters. The description adds context that the source parameter accepts raw content OR a URL (both handled automatically), which reinforces the schema. budget_pence is not elaborated beyond the schema's 'max spend in pence' description, but the behavioral note about spending balance gives it context. This is baseline 3 — schema does the heavy lifting.

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+resource ('Summarize') and details the supported input formats (text, HTML, Markdown, JSON, XML, URL, GitHub raw files). The title and tool name align well. It loses a point because it doesn't explicitly distinguish from closely related siblings like forcedream_extract_action_items or forcedream_extract_data, though the core summarization purpose is clear.

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 implies when to use it (document/URL summarization) but doesn't explicitly state when NOT to use it or name alternative tools. The mention of 'action items' overlaps with forcedream_extract_action_items sibling, which could confuse selection, and no exclusion criteria are given.

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