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

The description adds real context beyond the annotations: it discloses that the wrapper posts to the upstream ttb.utoronto.ca service, returns an upstream share id and a share link, and that only an anonymous share record is created. It does not mention that repeated saves create duplicate records, which the non-idempotent annotation hints at but the prose never confirms.

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 core action and return value, then the parameter requirement, then scope caveats. It is slightly wordy about the upstream URL mechanics, but every sentence contributes to correct invocation.

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?

With no output schema, the description correctly documents the return shape (upstream share id plus an https://ttb.utoronto.ca/#!/?t= link). Annotations already cover the safety profile (write, non-idempotent, non-destructive), so remaining gaps are minor, e.g. behavior on repeated saves.

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% and the single parameter is an unconstrained nested object (additionalProperties: true), so the description carries the burden. It does so well by specifying that "timetable" must be the TTB state object containing sessions, timetables, and plans, giving the agent the shape the empty schema omits.

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 and resource: it stores a serialized Timetable Builder state and returns a public share URL. That verb (store/save) plus the share-URL return clearly separates it from siblings like generate_timetable and retrieve_timetable, which produce or fetch rather than persist.

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 clarifies one boundary explicitly ("creates an anonymous share record only; it does not enroll students"), which tells the agent this is not an enrollment action. However, it never says when to prefer this over siblings such as retrieve_timetable or what precondition the state must come from, so usage is only implied.

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 declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: saved cookies are checked without opening a window, a saved cookie is not proof of a valid session, and last_verified is historical rather than an expiry — all of which shape how the agent interprets results.

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?

Four short sentences, front-loaded with the core purpose and followed by the parameter behavior and output caveats. Every sentence adds distinct value; none restates the name or schema.

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 one-parameter, non-destructive status read with no output schema, the description covers enough: scope of the read, refresh behavior, and the interpretation caveat for last_verified. It could say a bit more about what fields the status response contains for an agent to act on, but the essentials are present.

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?

The single parameter has 0% schema description coverage, so the description must carry the meaning — and it does, explaining that refresh=True re-checks both services against saved cookies with no login window. It does not describe the default (refresh=false) behavior explicitly, leaving one small gap.

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 gives a specific verb and resource: 'Get connection and login progress.' It also scopes what is NOT returned ('without exposing credentials or student records'), which helps separate it from data-returning siblings like get_course_details. It never names an alternative tool explicitly, so sibling differentiation 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?

It states a concrete use condition: 'refresh=True checks both services using saved cookies; it never opens a login window.' This tells the agent when to set the flag and clarifies that this tool is not the login path (uoft_login is). No explicit when-not guidance or named alternative is given, so it stops short of a 5.

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 declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and idempotency. The description adds that it finds read operations locally and requests schemas, providing context that it is a discovery tool with no side effects. However, it does not disclose any additional behavioral traits beyond what annotations already convey, so a 3 is appropriate.

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 description is two concise sentences that clearly state the purpose and the recommended usage pattern. It is front-loaded with the primary function and is free of redundant information. It earns a 4 for being efficient and well-structured, though it could potentially be expanded with minimal additional detail.

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?

The tool has 4 parameters, no output schema, and relies on annotations for safety. The description does not explain how to use the parameters, what the return format looks like, or provide examples. For a discovery tool, an agent would need to know what information it returns (e.g., names, descriptions, schemas) and how to specify queries. The description lacks this essential context, making it incomplete for effective use. A score of 2 is appropriate.

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?

The schema has 0% description coverage, so the description must compensate for the missing parameter documentation. However, the description does not mention any of the parameters (query, limit, detail, service). The parameter names and enum values (e.g., detail: names/descriptions/schemas; service: timetable/degree_explorer/acorn) provide some self-explanatory meaning, but the description adds no value to understanding the parameters. Given the low coverage, the description fails to compensate, so a score of 2 is justified.

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 clearly states that the tool finds read operations locally and requests schemas before calling unfamiliar operations. This identifies it as a discovery tool for available read operations and schema retrieval, distinguishing it from sibling tools like uoft_read (which likely performs the actual read). However, the term 'locally' is slightly ambiguous, so a 4 is appropriate.

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?

The description implies the tool should be used to discover read operations and to request schemas before invoking unfamiliar operations, providing a clear context for use. However, it does not explicitly mention alternatives or when not to use it, such as specifying that uoft_read is for actual reads or that this tool should precede any unfamiliar operation. The guidance is implied rather than explicit.

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 declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds meaningful specifics beyond that: exactly what is destroyed (local sessions and the encryption key) and for which scope (this MCP, both apps, not university-wide).

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 destructive action and then the scope caveat. No filler, and the most important constraint is not buried at the end.

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 zero-param, no-output-schema tool whose annotations carry the safety hints, the description is nearly complete, covering action and scope. The only unresolved ambiguity is what 'both apps' refers to and whether re-login is required afterward.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies.

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 (cancel/delete) and resource (local sessions and encryption key), and explicitly scopes it away from a university-wide logout. An agent can distinguish this from uoft_login and uoft_auth_status 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?

It gives clear context for use ('cancel login', local-only scope) and an explicit boundary ('not university-wide logout'), which tells the agent when this is inappropriate. It stops short of naming the alternative action (e.g. re-authenticating via uoft_login) after forgetting.

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?

The description discloses important behavior beyond the annotations: immediate return, a five-second wait with rechecking, saving the latest session, status staying in_progress, non-deletion on remember=False, and a security rule against supplying passwords or MFA codes. This gives the agent a strong model of side effects and timing.

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 description is dense but not bloated; the core behavior is front-loaded, followed by parameter-specific details and a safety note. Each sentence earns its place and no filler is present.

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, but the description covers what happens immediately, how status behaves during the wait, what remember=False does, and where to check progress. This is sufficient for an agent to invoke the tool and follow up correctly.

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 0%, so the description must compensate. It lists service options (degree_explorer, acorn, or both) and explains the meaningful semantics of remember=False as a fresh memory-only session without deleting saved sessions. Service values mostly echo the schema enum, but the remember explanation adds real value.

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 action ('Start official UofT browser login') and a clear resource, and immediately signals that it is asynchronous by returning while Duo is completed. It is clearly distinguishable from sibling auth-state tools like uoft_auth_status or uoft_forget_session.

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 concrete invocation context: saved sessions are reused when valid, remember=False starts a fresh memory-only session, and the agent should check uoft_auth_status for progress. It does not explicitly contrast with sibling session tools, but the intended usage is clear.

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?

The only behavioral addition beyond annotations is 'Snapshot handles last five minutes,' which is cryptic and could mean a time window, a snapshot mode, or something else. Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description adds little meaningful transparency. It does not contradict annotations, but the added statement is too vague to be useful.

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 description is very short, but brevity results in under-specification rather than conciseness. Neither sentence is actionable: 'Batch discovered reads' is vague, and 'Snapshot handles last five minutes' is ambiguous. Valuable space is wasted on unclear phrasing instead of essential usage details.

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?

With a complex nested input schema, no output schema, and zero parameter description coverage, the description is grossly inadequate. It does not explain how to structure requests, what operations are supported, what selection modes do, or what the tool returns. An agent would be unable to invoke the tool correctly based on the description alone.

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 0%, so the description must compensate for the undocumented parameters, but it does not. The phrase 'optional selection' vaguely references the selection object, yet it leaves the required 'requests' array and nested 'operation', 'arguments', and 'selection' fields completely unexplained. An agent cannot determine valid operation values, selection modes, or filtering semantics from the description.

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 says 'Batch discovered reads' but never names a specific resource or clear verb-object relationship. It is ambiguous what 'discovered' refers to and how this differs from uoft_discover or uoft_result. The name uoft_read hints at reading, but the description itself does not clarify the tool's core function.

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?

No guidance is given about when to use this tool versus any sibling. The description does not mention uoft_discover, uoft_result, or any alternative, nor does it state prerequisites or exclusions. The word 'Batch' implies bulk operations, but there is no concrete context for choosing this tool.

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 declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral context: 'without network access' and the note about handle expiration requiring a refetch. These details go beyond what annotations provide and help the agent understand operational constraints, though it doesn't describe the exact failure mode when the handle expires.

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 description is extremely concise—two short sentences with no filler. The primary behavior ('Select or page a snapshot without network access') is front-loaded, and the handle-expiry note is secondary. Every word earns its place; it is efficient and well-structured for quick scanning.

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?

Given the tool has a complex optional 'selection' parameter and no output schema, the description is far too sparse. It fails to explain what 'selection' does, what the expected return format is, or how to construct a valid selection. The note about handle expiration is useful but insufficient for an agent to call this tool correctly without additional inference. The schema's nested description partially compensates, but overall the description leaves critical gaps.

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 0%, and the tool description does not mention any parameters. Neither 'handle' nor 'selection' is explained in the description. The nested Selection schema has its own description, but the tool description itself provides no guidance on what these parameters mean or how they should be used, leaving a significant gap given the lack of schema-level descriptions for the top-level properties.

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 action ('Select or page') on a resource ('a snapshot') and notes the key constraint of no network access. It is clear enough to distinguish from general read operations, though it does not explicitly differentiate from sibling tools like uoft_read. The term 'snapshot' is somewhat vague, but the core purpose is understandable.

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?

The description implies that this tool is used when you already have a handle (since it mentions 'Refetch when the handle expires'), but it provides no explicit guidance on when to use this tool versus alternatives like uoft_read or uoft_discover. There are no stated exclusions or conditions for choosing this tool, leaving the agent to infer usage context.

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