Al-Taswia Iraqi Law Research

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

Annotations already cover readOnly/destructive/openWorld, so no credit for 'Read-only'. The description adds genuinely new behavioral context: a data-handling restriction ('Do not send client data') and a refusal policy (personal-status topics). No contradiction with 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?

Three short sentences, front-loaded with what is returned, then constraints. 'Read-only' is mildly redundant with readOnlyHint=true, but nothing is padded or buried.

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 carry the return contract; it says the page states a law name and article number but not the return format (raw HTML? extracted text? blocks?) or failure behavior for URLs that don't. Adequate for a single-URL fetch, but a gap remains.

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% for the single 'url' parameter, so the schema already documents the domain and type. The description adds a constraint on the target page's content (must state a law name and article number) but no format, canonicalization, or error semantics beyond that.

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: returns ONE published al-taswia.com page that contains a law name and article number. This distinguishes it from the plural/list siblings search_articles and list_official_sources implicitly (single fetch vs. search/list), though neither sibling is named.

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 real exclusions — 'Do not send client data' and 'Personal-status topics are refused' — which tell the agent when it must not call the tool. It does not, however, point to an alternative tool (e.g. search_articles) for the refused cases, so routing guidance is incomplete.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered; the description redundantly restates 'Read-only' but adds genuinely new behavior: a refusal rule for personal-status topics and a privacy constraint against client data. That refusal semantics is the valuable disclosure.

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 short sentences, front-loaded with the scope, then the safety hint, then the input rules. Every sentence carries information, though 'Read-only' duplicates the annotations and is the one low-value clause.

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 single-parameter read tool with no output schema, the description covers scope, input expectations, and refusal conditions adequately. What is returned (link format, ordering, count) is unspecified, but that is a minor gap for this tool's complexity.

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 single 'topic' param is documented as 'Topic to match against published pages', which the description essentially repeats. The 'not client data' note adds a small usage nuance but no format or matching-syntax detail beyond the schema, so 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 official legislation links') plus a scoping constraint ('already cited on published https://www.al-taswia.com pages'). This distinguishes it from get_article and search_articles, which deal with article content rather than legislation citations, though the description never names those siblings to make the boundary explicit.

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?

Provides explicit input guidance ('Send a topic, not client data') and a hard exclusion ('Personal-status topics are refused'), which tells the agent when the call will fail. It stops short of naming an alternative tool for the refused or non-matching cases.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered; the description's 'Read-only' is largely redundant. However, it adds real operational behavior the annotations cannot: personal-status topics are refused and every answer is grounded in a law name, article number, and page URL.

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?

Six short sentences, each earning its place, with the primary purpose front-loaded and the constraints following in priority order. No filler or repetition beyond the minor duplication of the read-only annotation.

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, and the description compensates by describing the return shape (law name, article number, page URL). Combined with the input constraints and refusal rule, an agent has everything needed to call and interpret this 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 meaningfully constrains the 'query' parameter by specifying it must be a topic rather than client names, contact details, or case files. That adds content semantics beyond the schema's bare 'Words to find in the published pages.'

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 (search) and resource (pages already published on a named site), which naturally separates it from get_article and list_official_sources. It does not name a sibling explicitly, but the scope is unambiguous enough that an agent can distinguish the tools.

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 concrete input guidance ('send a topic, not client names, contact details, or case files') and an explicit exclusion ('personal-status topics are refused'). It stops short of naming sibling tools or describing when to prefer them, but the when-to-use and when-not-to-use signals are clear.

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