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

With no annotations, the description carries the burden well: it discloses the two-phase upload handshake, that zeroDataRetention 'requires an eligible authenticated account' and should be omitted for anonymous keyless use, that redactPII requests content redaction, and that returns differ per phase (upload instructions vs parsed content, plus optional data.metadata.scrapeId). Gaps remain: no mention of credit/cost implications, file size limits, or failure behavior, which a 20-param no-annotation tool could still use.

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 with purpose and output modes, then organized into paragraph-per-concern (inputs, local vs hosted flow, behavioral flags, returns). Dense but justified for a 20-parameter tool; a few clauses, such as the scrapeId feedback note, are marginally more than an agent needs to invoke it.

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?

No output schema exists and the description only sketches return shapes ('upload instructions for hosted phase one or parsed document content'), so more return detail would help. Given 20 parameters including two nested objects, the description also omits how formats, jsonOptions, and queryOptions relate to each other, leaving meaningful gaps for a tool of this complexity.

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 only 30% across 20 parameters, so the description must compensate and only partly does. It clarifies filePath, uploadRef, pdfOptions.maxPages, redactPII, and zeroDataRetention semantics, but leaves many parameters undocumented in both places — formats, jsonOptions, queryOptions, onlyMainContent, includeTags/excludeTags, storeInCache, proxy, parsers, skipTlsVerification, removeBase64Images, conversationId, maxAge.

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 (parse) plus resource (one supported document) and enumerates the output artifacts (markdown, HTML, links, summary, targeted answers, schema-matched JSON) and supported input families (HTML, PDF, Word, RTF, OpenDocument, spreadsheets). It also explicitly routes remote URLs to the sibling firecrawl_scrape, so the agent can separate this from firecrawl_scrape/firecrawl_crawl without opening schemas.

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 when-to-use and when-not-to-use: 'Remote web URLs belong in firecrawl_scrape.' It also spells out the branching operational flow — local MCP reads filePath directly, hosted MCP requires two calls (filePath for upload instructions, then uploadRef), and warns 'do not send both fields together.' That is a genuine exclusion rule an agent could otherwise get wrong.

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