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

Annotations only declare the mutation/non-idempotent profile, but the description goes further: state is saved and expires_at refreshed on success, invalid/stale requests and unknown/expired run_ids fail without advancing, and prior-step replay is rejected. This is exactly the failure-mode and retry context the annotations cannot carry.

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 in one sentence, then tightly scoped bullets for triage, primary review, early stop, success, failure, and retry. Every line encodes a distinct rule; no filler or repetition of schema text.

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 7-parameter, non-idempotent orchestration step with an output schema, the description covers routing, per-step parameter requirements, failure semantics, and recovery, and it correctly does not re-explain return values. An agent has everything needed to call it correctly on the first attempt.

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 baseline is 3, but the description adds cross-parameter conditional logic the schema does not express: risk_signals is required only with the final completed primary-review profile ({} when none), completed_profile must echo current_profile, and route selectors must be omitted on early stop. It does not restate the enum values themselves, which is correct.

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 ("Record one active QA step's result") plus the return contract (updated state and next_action). It explicitly distinguishes itself from the two nearest siblings, finish_qa_orchestration and get_qa_orchestration, so an agent can route without opening another 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 explicit when/when-not rules and alternatives: use finish_qa_orchestration at awaiting_host_outcome, match the recorded outcome after early stops, do not call on a lost response but read get_qa_orchestration(run_id) instead. Per-step selection rules (triage picks exactly one bundle or profile; early stop omits selectors) leave nothing to inference.

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 destructive, idempotent, and non-read-only, but the description adds material context beyond them: deleted=true confirms absence even for unknown/expired IDs, irreversibility that survives restart, storage-failure behavior where memory stays intact, and the explicit note that host tasks and model executions are unaffected. These are exactly the operational details annotations cannot convey.

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 imperative sentence, then a bulleted block where each line carries a distinct fact (mutation behavior, idempotency, irreversibility, failure recovery, unaffected systems). No sentence restates the name or the annotations verbatim, and there is no padding.

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 an output schema present, the description need not explain return fields, and it correctly stops there. For a single-parameter destructive mutation with full annotation coverage, everything an agent needs to call it safely and recover from edge cases is 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?

Schema coverage is 100% and the schema itself documents the qar- pattern, so the baseline is 3. The description nonetheless adds dispatch-relevant meaning: run_id can select a session at any stage with no prior advance or finish, and it points at list_qa_orchestrations as the recovery path for an unknown 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?

The description opens with a specific verb and resource ('Delete one QA session from memory and configured recovery storage') and immediately distinguishes itself from the sibling that shares its domain by naming finish_qa_orchestration as the retain-outcome alternative. An agent can differentiate it from advance/get/list/prepare with no schema inspection.

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 when to use this tool ('to retain a final QA outcome, use finish_qa_orchestration' implies deletion is for discarding), relaxes a constraint ('no prior advance or finish required'), and routes the agent to list_qa_orchestrations to recover a lost ID with instructions for disambiguating matches. Explicit alternatives and conditions are provided rather than 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?

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false). It discloses idempotent semantics concretely (same outcome returns the retained terminal session; a different outcome raises 'conflicting final outcome' with status unchanged), the TTL expiry (1800s default), eviction/restart removal, and that removed run_ids cannot be deduplicated.

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 purpose, then bulleted behavioral cases (same outcome / different outcome / premature call) and a closing lifecycle sentence. Dense but every sentence carries distinct information with no repetition of the 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?

An output schema exists, so return values need no explanation, and the description instead covers the error paths, state preconditions, and session lifecycle that an agent must know to call this correctly. Nothing material is missing for a two-parameter finalization tool.

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 the baseline is 3, but the description adds real meaning: run_id must be the retained session id from start_qa_orchestration and the outcome choice is constrained by upstream early-stop state. The enum values themselves are already documented in the schema, so it does not fully re-earn a 5.

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 ('Finalize the whole QA run's outcome') and immediately scopes it against the sibling that handles the other half of the work ('active step results belong to advance_qa_orchestration'). An agent can distinguish it from advance_qa_orchestration, start_qa_orchestration and the get/list siblings without opening a 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 explicit preconditions and timing: call after synthesis, use the retained run_id while the session is at awaiting_host_outcome, and ensure the outcome matches a partial/blocked early stop recorded by advance_qa_orchestration. It also warns that a premature call returns 'outcome is not ready', so when-not-to-call is covered.

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 flag readOnly/idempotent/closed-world, and the description adds genuinely new behavior: reads do not extend expires_at, the id is server-scoped, and local stdio access needs no extra credentials. These are exactly the operational facts an agent cannot infer from the annotations.

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 what is read, then scoping, then error/recovery routing, then disambiguation from siblings. Every sentence carries distinct information; none is filler.

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 an output schema present, return values need no further explanation, and the description still summarizes the returned state. For a single-parameter read tool, nothing an agent needs to call it correctly or recover from failure is missing.

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% and the pattern plus reuse warning are already in the schema, so baseline is 3. The description adds real meaning by specifying the id must be used on the server retaining that session and that it can be recovered from list_qa_orchestrations, which the schema does not state.

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 (Read) and resource (one run_id's retained state) and enumerates exactly what is returned: status, current step, next action, model policy. It is immediately distinguishable from sibling readers like get_qa_orchestration_model_policy and list_qa_orchestrations.

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 covers when to use it (resume or reconcile a lost advance_qa_orchestration response), what the error cases mean (`unknown run_id`, `expired session`) and the recovery path (start_qa_orchestration), and what to do if the id is lost (list_qa_orchestrations). It also names the alternatives for other needs (model policy, review progress, final outcome).

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 openWorldHint=false. The description adds useful context beyond them: the catalog is static and comes from the installed server's bundled definitions, active sessions and configured models do not change it, and task-type recommendations are shortlists rather than restrictions.

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 front-loaded with the purpose, then moves into usage conditions, cross-references, and a final caveat. The bullet list for related tools is efficient and nothing reads as filler.

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-parameter, read-only discovery tool with an output schema, the description provides everything an agent needs: what it returns, when to call it, what preconditions are unnecessary, and how it relates to sibling tools. Return-value details are appropriately left to the output 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?

There are zero parameters, so the rubric baseline is 4. The description adds a small amount of useful clarity by stating that no session or arguments are required, though there is no parameter syntax or structure to explain further.

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: reading the static profile/bundle catalog, with its contents enumerated (specialists, review scopes, ordered routes). It is clearly distinguishable from siblings like prepare_qa_orchestration and start_qa_orchestration because it describes discovery, not session mutation.

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 says to use this before creating a session or choosing its triage route, and notes that no session or arguments are required. It also provides next-step alternatives for detailed checklists, session creation, route setting, and listing session IDs, and explains how to choose a bundle versus a single profile.

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 readOnly, idempotent, and closed-world behavior, but the description adds substantial non-obvious context: it reads an in-memory snapshot rather than the current policy file, requires a server restart after file changes, creates no session, contacts no provider, and does not verify which model the host executed.

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-loads the purpose and scope, then concisely groups usage routing into bullets and behavioral caveats into tight sentences. Every sentence adds distinct value with no repetition or wasted space.

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 output schema exists, so return values need not be described. The description covers what is read, when to use it, alternatives, and important behavioral caveats, making it complete for a zero-argument inspection tool.

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 has zero parameters, so the baseline is 4. The description confirms 'takes no arguments,' which is consistent with the empty schema and leaves no parameter ambiguity.

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: reads server-wide model settings for every stage, listing provider, model IDs, and reasoning. It also distinguishes itself from siblings by explicitly naming get_qa_orchestration(run_id) and start_qa_orchestration as alternative tools for different needs.

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 says to use it to inspect the policy loaded for new sessions and notes it takes no arguments. It routes the agent clearly: existing session/current-stage policy uses get_qa_orchestration, and creating a session with these settings uses start_qa_orchestration.

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/openWorldHint=false, so the safety profile is covered; the description goes further with non-obvious behavior the schema cannot express: reading does not extend TTL, expired/evicted sessions are unrecoverable, sorting is expires_at desc then run_id desc, empty result means nothing retained, and post-restart only unfinished local-storage sessions reappear.

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 opening sentence states purpose, the second sentence front-loads the primary use case and alternatives, and four tight bullets carry only non-redundant behavioral facts (TTL, sort, restart, empty semantics). No sentence is filler.

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?

Although an output schema exists (so return-field documentation is not required), the description still supplies everything an agent needs that the structured fields do not: empty-result interpretation, sort order, TTL non-extension, and restart scoping. Nothing material to correct invocation is missing.

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?

There are zero parameters and schema description coverage is 100%, so the baseline is 4. The description explicitly confirms "Takes no arguments," which is the only parameter-level fact available and is already fully specified by the schema, so it cannot exceed the 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?

States a specific verb and resource ("List non-expired QA session identifiers and brief metadata") and immediately distinguishes itself from get_qa_orchestration, which returns "full state" rather than a list. An agent can tell from the description alone which of the siblings to call for a lookup versus a state read.

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 an explicit use case ("Recover a lost run_id by matching task type, route, and stage; confirm if several match") and routes to the correct alternatives by name for other needs (get_qa_orchestration for full state, get_qa_orchestration_model_policy for server policy). It also states a when-not: expired or evicted sessions are unrecoverable.

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?

Beyond the readOnlyHint/openWorldHint/idempotentHint annotations, it discloses that this is a local lookup over bundled definitions that executes no reviews and calls no models, that results are a pure function of agent_profile, and that invalid values fail input validation and should be retried with a listed enum value. This error-handling and no-side-effect disclosure is genuinely non-obvious context.

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?

Purpose is front-loaded in the first sentence, followed by tightly scoped bullets for the two usage paths and a short closing note on local behavior and validation. Every sentence carries information; nothing is redundant with the schema or annotations.

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 one required enum parameter, a 100%-covered schema, and an output schema present, the remaining burden is routing and behavior – both covered (catalog vs. session path, advance_qa_orchestration alternative, determinism, validation failure). Nothing an agent needs in order to call this correctly is missing.

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% and the enum description already defines all ten profiles, so the schema carries the baseline. The description still adds selection guidance not in the schema: results depend only on agent_profile, choose from changed files and confirmed stack, and preserve review_profiles order when handling bundles.

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 first sentence names a specific verb and resource ('Return one specialist's fixed ReviewRoute checklist') and enumerates the exact payload fields (profile, display_name, focus, required_sections, constraints, escalation_signals). It is unmistakably a local definition read, distinct from advance_qa_orchestration, get_qa_orchestration_catalog, and the other siblings.

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 the trigger ('Use before reviewing one scoped concern'), an important precondition ('no session is required'), and then splits the two concrete workflows: standalone review via get_qa_orchestration_catalog(), and session primary_review passing the latest current_profile as agent_profile. It also names advance_qa_orchestration as the alternative for applying a session route, so when-to-use and when-not are both 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 only cover safety/idempotency flags; the description adds substantial behavioral context beyond them: TTL expiry (1800s default), 100-session capacity, purge/eviction behavior, and the specific 'session limit' error when only an active session could free capacity. This is exactly the operational detail annotations cannot express.

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 purpose sentence, then a routing sentence, then tight bulleted constraints. Every sentence carries distinct information with no filler or repetition of the 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?

Output schema covers return values, so the description is not obliged to describe them. Combined with annotations and the schema, the description supplies the lifecycle (TTL, capacity, eviction, error) an agent needs to call it 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 coverage is 100% and the enum is fully self-documented, so baseline 3 applies. The description still adds real meaning by clarifying what task_type does and does not do ('narrows the bundle shortlist', 'host still selects the review route', 'not a risk level'), correcting a plausible misreading.

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 (create) and resource (content-free QA session) with the timing constraint (call once before triage) front-loaded. It explicitly contrasts with prepare_qa_orchestration, so the agent can separate it from siblings without opening schemas.

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 explicit when ('call once before triage') and when-to-use-the-alternative ('Use prepare_qa_orchestration for a stateless profile checklist'). It also clarifies that every call creates a separate session, preempting accidental reuse.

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