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

Annotations only declare the basic safety profile (readOnlyHint=false, destructiveHint=false), and the description adds substantial context beyond them: a 2-hour idle expiry that loses gathered sources, saved briefs and versions remaining unaffected, new conversations starting fresh runs from the latest brief, and idempotency-key retry semantics. It also discloses the prompt-injection boundary for brief prose, notes and excerpts, which is exactly the kind of behavioral trait an agent needs here.

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 first sentence is front-loaded with the core action and side effect, and the lifecycle rules that follow are each short and operational. It is dense with rules but most earn their place; the closing prompt-injection sentence is defensible security context though not strictly about invoking this tool.

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 6-parameter, non-read-only tool with no output schema, the description covers lifecycle, expiry and retry behavior well but leaves real gaps: it never says what a successful call returns (run identifier, created brief), and three of six parameters (lenses, question, ticker/company_id split) are undocumented anywhere given 0% schema coverage.

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 0%, so the description must carry parameter meaning and only partly does: it explains idempotency_key (new key for a new run, same key only for retry) and enumerates the playbook values (understand, update, challenge) with the instruction to use them every run. It says nothing about the lenses enum values (price, business, shareholders, earnings_power, resilience), the question field, or how ticker differs from company_id.

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 ("Start research") plus the side effect ("automatically create the company brief"), and names the sibling that ends the lifecycle ("finish it with complete_research_run there"). An agent can distinguish this from complete_research_run and the get_* siblings without opening any 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 concrete when-to-use conditions: start another run with a new idempotency key if the conversation reaches a conclusion the saved version lacks, and only retry a call with the same key. It also states the run is scoped to one conversation and directs the agent to complete_research_run rather than starting a second run. It stops short of explicit when-not-to-use guidance such as what to do if a run is already active.

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