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

Goes well beyond the readOnly/idempotent annotations: deterministic and free with no model call, strict source-trust rules (only the entity's own domain counts; search results and third-party text never create routes or names), gating of intro_path on connected_evidence per hop, and an explicit safety instruction that terms_conflict yields auto_execute false and must not be executed. It also flags evidence quotes as untrusted content, which is important prompt-injection context an agent would otherwise lack.

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 the action and prerequisites, then the return shape, then the trust and safety rules. Every sentence carries information, though the long enumeration of route types and fields is dense and could be tightened. No filler or repetition.

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?

There is no output schema, and the description takes on that burden by enumerating route types and their accompanying fields (url/address, requirements, cost, speed, conflicts, evidence quotes), plus the discovery_plan output. For a nested six-parameter tool this is nearly complete; the main gap is the unexplained constraints object and how goal influences ranking.

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 67%, and the description compensates usefully for the most consequential inputs: what 'entity' means (name, domain), that 'evidence' must be official pages fetched via scrape/search, and that connected_evidence is the user's own mail/contacts/network session with each hop sourced. It does not explain 'constraints' (max_cost, exclude_types) or clarify how 'goal' shapes ranking, so a few parameters remain schema-only.

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 states a specific operation: given a goal and entity, compare and rank the ways to reach that entity, returning route types in preference order. This is distinguishable from alterlab_scrape/alterlab_search, which it names as evidence sources. It stops short of explicitly contrasting with execution-oriented siblings such as alterlab_hands_run or alterlab_hands_access, so the boundary between planning and acting is implied rather than stated.

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?

'Before acting on a goal with a company or person, compare the ways to do it' gives a clear trigger and a clear sequencing rule relative to acting. It also specifies input prerequisites (pages fetched via alterlab_scrape or alterlab_search) and a hard stop ('do not run that route yourself' on terms_conflict). It does not name which sibling to use instead when the user wants execution rather than route comparison.

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