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

With no annotations, the description carries the burden and does disclose useful behavior: OCR for scans, clause splitting, per-clause risk, a synchronous wait of about one to two minutes, and output equivalence to get_contract. However, it does not state whether replacing a document is reversible, what permissions are required, or what happens on failure, which are important for a mutating, long-running tool.

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?

Three sentences, front-loaded with the core action and pipeline, then the two usage modes, then timing and return behavior. No filler; every sentence carries useful information.

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 complex, synchronous, mutating tool with an output schema present, the description covers the pipeline, timing, and create-vs-replace modes. It omits some operational details such as failure behavior and prerequisite validation, but those gaps are relatively small given the output schema and detailed parameter schema.

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 schema already explains each parameter. The description adds useful grouping by distinguishing the contract_id replacement mode from the new-contract creation fields, but it does not add syntax, constraints, or semantics beyond what the schema already provides.

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+resource: uploading a contract and running PAKT's analysis pipeline. It names the processing steps and tells the agent the return is equivalent to get_contract, making its purpose clear relative to at least one sibling.

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?

Explicitly explains the two usage modes: pass contract_id to replace an existing document, or pass company/title/contract_number/start_date/our_role to create a new contract. It gives clear context but does not explicitly state when-not to use this tool or name alternative siblings like compare_amendment.

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?

With no annotations provided, the description carries the full burden. It does disclose that uploading triggers an analysis that must be waited on and returns conflict counts by severity, but it omits permissions/auth requirements, whether uploading an amendment persists or modifies data, and any rate or failure behavior.

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 output content is front-loaded in the first sentence and the parameter modes follow. It is dense but every clause carries information; the second sentence is long but functional. No filler sentences.

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?

Six parameters with one required and an output schema that already covers return values, so the description need not detail results. It correctly covers the main invocation modes, but slightly over-describes outputs it didn't need to and leaves wait_seconds/analysis-timing behavior to the schema.

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%, so baseline is 3. The description goes beyond the per-parameter schema text by tying file_path, signed_date and amendment_id into mutually exclusive modes ('neither for all of the contract's amendments'), which adds real meaning about how the parameters combine. It does not, however, explain wait_seconds semantics beyond what the schema already says.

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 verb+resource: it compares a contract's amendments against the base contract and returns conflicts categorized by base clause, direction (against us / in our favour) and severity (red/yellow/green). It is clear what the tool does, but it never mentions the sibling analyze_contract, so differentiation from neighbors is left to inference.

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?

It gives explicit operational routing: 'Give file_path and signed_date to upload a new amendment and wait for its analysis; amendment_id for one amendment; neither for all of the contract's amendments.' That is clear guidance on invocation modes, though it offers no when-to-use-vs-analyze_contract guidance or prerequisite/exclusion conditions.

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?

With no annotations provided, the description carries the full behavioral burden, yet it only enumerates returned fields and says nothing about whether this is a safe read, whether it is expensive, what authorization it needs, or how large the payload can get. The scoping to a single contract is implied but never stated as a behavioral constraint.

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?

A single dense sentence front-loads the resource ('One contract's overview') before listing contents. Nothing is wasted, though the long comma/chained enumeration makes it slightly harder to scan than a two-sentence split would be.

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 the heavy focus on returned fields is partly redundant, and the description leaves usage and sibling selection entirely unaddressed for a tool whose siblings overlap in purpose. It is adequate — the agent knows what it gets back — but incomplete on when to prefer 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 description coverage is 100% with only two parameters, so contract_id's provenance ('from list_contracts') and include_text's effect ('also return each clause's full text') are already documented in the schema. The description adds nothing about either parameter, which is acceptable at full coverage but not above baseline.

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 names the specific resource ('One contract's overview') and enumerates exactly what comes back: details, verdict components, clause color counts, per-clause risk level, and amendments with conflict counts. It is clear this fetches a single contract, distinguishing it implicitly from list_contracts, but it never explicitly contrasts itself with siblings like analyze_contract or compare_amendment.

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 statement of when to call this versus analyze_contract or list_contracts, nor any prerequisite or exclusion. The only procedural hint is buried in the schema (contract_id 'from list_contracts'), not the description. An agent must infer usage entirely from the sibling names.

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?

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing beyond the fact that this is a read/list operation. There is no mention of ordering, pagination, result limits, or any permission requirements, which matters for an account-wide listing.

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?

Two short sentences, front-loaded with the action and scope, and the routing hint comes last. The enumeration of returned fields is slightly redundant given an output schema exists, but it costs little.

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 both optional filters are covered by the schema. The remaining gap is operational behavior (ordering, pagination/limits) that an agent listing an account's contracts would reasonably want.

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 both filter parameters (status, company) are already fully documented in the schema; the description only alludes to them in passing. Per the baseline rule, a 3 is appropriate when the schema does the heavy lifting.

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 ('List the account's contracts') plus the scope of the listing (account-wide, with the fields it surfaces). It also names the sibling it is not, so an agent can separate it from get_contract without opening either 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?

Explicitly routes single-contract risk lookups to get_contract, giving a clear use/use-other split. It stops short of covering the other siblings (analyze_contract, compare_amendment) or stating when a listing is the wrong choice.

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