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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds a genuine behavioral trait beyond them — that the call is cheap and transfers no record data — but says nothing about permissions, errors on invalid model names, or how an omitted domain affects 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?

A single front-loaded sentence with zero waste; the key verb and resource come first and the efficiency note is a compact qualifier. Nothing could be removed without losing 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?

An output schema exists and the parameters are fully documented, so return values and input format needn't be explained. The remaining gap is minor: no note on what happens with an unknown model or which models are accessible, but an agent has what it 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 description coverage is 100%, with both 'model' and 'domain' fully documented including operator syntax and the empty-domain behavior. The description mentions the domain concept but adds no syntax or format detail beyond the schema, so the baseline 3 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?

The description gives a specific verb ('Count') and resource ('records matching a domain'), which is clearly distinguishable from search_records or read_record by the counting semantics. It does not explicitly name a sibling as the alternative, so it stops short of a 5.

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 parenthetical '(cheap; no data is transferred)' implies you should reach for this when you only need a total rather than the records themselves, but the description never says 'use this instead of search_records when...'. Usage must be inferred from the efficiency hint rather than 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 declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds valuable context beyond annotations: it discloses which field attributes are returned (type, label, required, readonly, relation, selection values), that permissions for the current user are included, and that required fields are ordered first. It does not describe response size, performance, or error behavior, but the output schema covers return shape.

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 with no wasted language. The key purpose and returned information are front-loaded, and the ordering detail is placed efficiently after the main description.

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 a rich input schema with 100% description coverage, explicit read-only/open-world annotations, and a present output schema, the description is nearly complete for an agent to call it correctly. The main gap is guidance on when to choose this tool over siblings, though that is more of a usage concern.

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 all three parameters are already well documented in the input schema. The description does not add parameter-specific semantics such as how field_query filters fields or when include_technical should be used, so baseline 3 is appropriate.

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 uses a specific verb ('Describe') and resource ('a model's fields') and enumerates the returned field attributes and permission information. It clearly distinguishes schema introspection from sibling tools like list_models (which lists models) and read_record (which fetches records).

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 usage for inspecting a model before querying or reading records, but it does not explicitly state when to use this tool versus list_models, search_records, or read_record. No exclusions or alternative-routing guidance is provided.

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 and openWorldHint, so safety of the call is known. The description adds non-obvious context: models blocked by the safety policy are never listed, which explains why a model the agent expects may be absent. Pagination/limit behavior is left to the schema.

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, zero waste. The core purpose is front-loaded and the scope caveat follows immediately.

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 annotations covering read-only semantics and an output schema present, the description only needs to establish scope and any surprising behavior — which it does via the access scope and safety-policy exclusion. Only minor gap is that limit/pagination behavior is not mentioned.

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 each parameter is already fully documented, including that the query filters on technical name or label. The description only restates that filtering is by name, adding nothing beyond the schema. Baseline 3 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 and resource: 'List the Odoo models this server can access.' The scoping phrase 'this server can access' plus the safety-policy note makes the domain clear. It does not explicitly contrast with siblings like describe_model, but the resource (models vs records) already separates it.

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?

Usage is only implied ('optionally filtered by name'). There is no statement of when to prefer this over describe_model or search_records, and no prerequisites or exclusions beyond the safety-policy note.

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 and openWorldHint, so safety is covered. The description's one behavioral claim — that omitting `fields` returns "all non-binary fields" — conflicts with the schema, which says omitting returns a compact default set and ['*'] is needed for all non-binary fields. That misleading default is a real defect for an agent deciding what to pass.

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?

One short sentence with the core operation front-loaded and no filler. It is arguably too terse given the tool's scope, but nothing in it is wasted.

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 read-only profile is covered by annotations. Still, the field-default discrepancy leaves an agent unsure what a bare call actually returns, which is the one thing this description should have settled.

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 schema already explains model, record_id and the fields wildcard/default behavior in detail. The description only restates the `fields` behavior, and restates it inaccurately, adding no correct meaning beyond the schema.

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 ("Read a single record by id") and the id-based lookup implicitly separates it from search_records. It never names a sibling tool, so the differentiation is inferred 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?

"by id" implies you must already know the record id, which is a usable usage cue, but there is no explicit when-to-use versus search_records/count_records. The only routing hint ("Use describe_model...") lives in the schema, not the description.

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=true and openWorldHint=true, so safety is covered, and the description goes further by disclosing the pagination contract: total match count, current page, and next_offset only when more records exist. That is genuinely useful behavioral context beyond the annotations, though it says nothing about cost, result caps beyond the schema's limit, or access 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?

Two short sentences with the core action front-loaded and the return contract following. No filler, though the sentence break mid-thought and the absent sibling guidance mean it is efficient rather than exemplary.

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 and the input schema is fully documented, so the description does not need to restate parameters or return shape, and it correctly focuses on the paging behavior. What is missing is the disambiguation from read_record and count_records, which is the one thing the structured fields cannot supply.

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% and the domain, fields, order, limit, and offset parameters are all documented in detail in the schema, so the schema carries the load. The description adds no parameter-level meaning (no default limit mention, no domain syntax note), so the baseline 3 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?

Names a specific verb (search) and resource (records) plus the two things it does: filter by a domain and project a field set. It is clear on its own, but nothing in the text distinguishes it from read_record or count_records, so an agent must infer the boundary from the names alone.

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?

Usage is only implied: the mention of a domain and paging suggests bulk/filtered retrieval, but there is no explicit 'use this instead of count_records when you need the rows' or 'use read_record for a single known ID'. With three closely related siblings, the guidance an agent actually needs is left to inference.

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