RedFlagLease

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

Annotations cover the safety profile (destructiveHint=false, openWorldHint=true), and the description adds genuinely useful behavior beyond them: a ~45 second runtime expectation, the fact that a report is hosted externally at redflaglease.com, and a 'not legal advice' disclaimer. It does not clarify why readOnlyHint is false for what reads like a scan, which is the one behavioral loose end.

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, then input instruction, then return contents, latency and disclaimer. Three sentences with little waste; the long parenthetical enumerating report contents is slightly dense but each item is informative.

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 compensates well by enumerating what comes back: every flagged clause with severity, risk, state rule/citation, plus a report link containing quoted clauses, fixes, missing protections, questions and a negotiation email. Latency, external dependency and legal disclaimer are all disclosed, so an agent has everything needed to call and interpret it.

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% with only two parameters, each already documented (two-letter state code, full lease text with a minimum length). The description reinforces 'Pass the full lease text' but adds no format or constraint detail beyond the schema. Baseline 3 applies when the schema carries the parameter burden.

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 with clear scope: 'Scan a US residential lease for risky, unusual or likely unenforceable clauses under that state's tenant law.' The 'US residential' qualifier usefully bounds the domain, and 'Pass the full lease text' signals this is a document-scanning tool rather than a Q&A tool. It never names the sibling tenant_law, so sibling differentiation is left implicit rather than explicit.

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?

Scope limits ('US residential lease') imply when the tool applies, and 'Pass the full lease text' implies the input mode. However, there is no explicit when-not-to-use guidance (commercial leases, non-US leases) and no routing to the tenant_law sibling for general questions. Usage is inferable but not stated.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description meaningfully supplements this by stating the data is verified against official statutes and that every rule carries a citation and source link. This provenance context is valuable and not present in the 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?

It is front-loaded with the core scope statement followed by a single informative enumeration of returned rule types. Slightly list-heavy but every item earns its place by telling the agent what content to expect.

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 read-only, single-parameter lookup with a complete schema and full annotation coverage, the definition is nearly complete, and it even describes the returned content (rules with citations/source links). The only minor gap is that return format/pagination is not addressed, though no output schema exists to lean on.

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 description coverage is 100%, so the single 'state' parameter is already fully documented in the schema with format and examples. The description only reinforces the one-state scope ('for one US state') and adds no syntax or format detail beyond the schema, matching the baseline of 3 for high coverage.

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 opens with a precise scope statement ('Verified landlord-tenant rules for one US state') and then enumerates the exact rule categories returned, so an agent knows exactly what it gets. It is clear but does not explicitly differentiate itself from the sibling check_lease.

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?

There is no explicit when-to-use statement and no mention of the sibling tool check_lease or any exclusion condition. The intended usage is only weakly implied by the content enumeration, leaving the agent to infer when this is preferable to checking a specific lease.

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