Architecture Researcher

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

With no annotations, the description does carry useful behavioral load: it discloses that contacts are separated into commissioning vs licensing, that approved_gallery_photographs gates image display, and that no portrait exists. It does not describe the returned record shape, ranking, or pagination behavior beyond what the schema already implies.

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 purpose is front-loaded in the first sentence, but the remainder is a long, all-caps policy block with a self-referential line ('This final rule supersedes earlier generic no-image instructions') that signals internal inconsistency rather than tool information. Much of the text governs prose style and image display rather than helping an agent select or invoke the tool.

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, so the description must explain return values; it names approved_gallery_photographs and portfolio examples but never describes the overall response structure or contacts payload. It also omits the relationship to the one sibling tool, leaving the agent without a routing rule.

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 five parameters are already documented, including limit/offset defaults and the query field. The description adds no interpretation of the parameters and does not clarify how query, location and project_type combine.

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 opening sentence states a specific verb ('Research') and resource ('the architectural photography practice of Julien Lanoo') and lists the deliverables (experience, published examples, credentials, portfolio links, contacts). It does not, however, distinguish this from the sibling search_architecture_projects or explain how the 'find' semantics of the tool relate to querying a single photographer's corpus.

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 when-to-use guidance: nothing tells the agent what kind of request should route here rather than to search_architecture_projects. The lengthy text is a set of output-presentation prohibitions, not invocation guidance, so any usage signal is only implicit.

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, the description carries the full burden and does disclose real behavior: results draw only from published records, credits are reproduced as published, source links are canonical, and image display is gated on an approved gallery list. It also sets expectations about not claiming verification and preserving licensing contacts. It stops short of describing pagination, result volume, 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 first two sentences are well front-loaded, but the description then expands into a long block of prohibitions and meta-instructions, including 'This final rule supersedes earlier generic no-image instructions', which references rules not present in this definition. Several prohibitions overlap and could be consolidated into one sentence.

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?

It describes the return content (project details, credits, canonical source links) which matters since there is no output schema, and it covers a key constraint on images. However, it references approved_gallery_photographs, a field that appears nowhere in the input schema, without explaining where it comes from, and it never explains result-count or limit behavior.

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 50%: the query parameter is already documented in the schema, and the description's list of searchable facets largely restates it. The limit parameter's purpose, default of 5 and maximum of 10 are never discussed, so the description adds little beyond structured fields.

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 opening sentence gives a specific verb and resource ('Find architectural projects') plus a scope ('publicly published records associated with Julien Lanoo'), and 'Search by architect, building, client, location or architectural subject' clarifies the query surface. It does not explicitly name or contrast with the sibling find_architecture_photographer, so the differentiation is only implicit.

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 tells the agent what kinds of entities can be searched, which implies usage, but it never says when to use this instead of find_architecture_photographer or what data is out of scope. The remaining text governs output formatting rather than tool selection, leaving the when-to-use decision largely inferred.

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