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

Annotations only supply openWorldHint=false and destructiveHint=false; the description goes well beyond that by confirming nothing is persisted, enumerating two hard import blockers (missing date, mismatched company name), and specifying that confidence scores and warnings must be surfaced verbatim in plain language. That is real behavioral context an agent cannot infer from structured fields.

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?

Front-loaded correctly: the no-write guarantee and the pre-import sequencing come first, before the presentation and blocking-condition details. It is long and prescriptive about output layout, but each block (field order, cap-table figures, blockers, web-parity note) maps to a distinct decision the agent must make, so little is pure padding.

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?

An output schema exists, so return values need no explanation, and the description still covers workflow, confirmation, blockers and reporting obligations. The one residual gap is how the document reaches the tool, which matters for a two-parameter tool with an undocumented required formationId.

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 50% and neither parameter carries a description in the schema, so the description carries partial burden. 'Reads a SAFE PDF' loosely implies sourceS3Uri is the document location, but formationId and the relationship between the two inputs (is the PDF already attached to the formation, or supplied as a URI?) are never clarified. Baseline 3 is appropriate given the description only marginally compensates.

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 (reads a SAFE PDF, returns its terms) and immediately scopes it with 'WITHOUT saving anything', which cleanly separates it from the mutating sibling cap_table_import_safe. An agent can tell what this does and what it does not do without opening the schema.

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?

Gives explicit sequencing ('Always call this before ImportSAFE'), an explicit prohibition ('never import a SAFE the user has not seen'), and the human-confirmation requirement. It also names the alternative flow (the web upload screen) whose wording and order should be matched, so the agent knows both when to call it and what the surrounding workflow expects.

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